Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negative statements or conditions related to performance or adequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "not", less, or "+" signs

    np_acts-logits-general · gemini-2.0-flash

    adequacy or fulfillment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    -0.54
    CrossRef
    -0.54
    AndEndTag
    -0.48
    SharedDtor
    -0.47
     betweenstory
    -0.43
    AddTagHelper
    -0.43
    inSlope
    -0.43
     abger
    -0.42
    rinfo
    -0.40
    VideoCapture
    -0.40
    POSITIVE LOGITS
     properly
    0.60
     adequately
    0.55
     satisfactorily
    0.51
     sufficiently
    0.51
     proper
    0.50
     satisfactory
    0.46
     fulfilling
    0.45
     fulfill
    0.45
     fully
    0.44
     fulfil
    0.43
    Act Density 0.601%

    No Known Activations