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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating attention or introduction of a topic

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

    Sentences starting with "Here"

    np_acts-logits-general · gemini-2.0-flash

    here's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NUMX
    -0.69
     ujednoznacz
    -0.67
    Ehrungen
    -0.64
     assoluto
    -0.63
     متعلقه
    -0.63
     CreateTagHelper
    -0.63
    moiselle
    -0.63
     Infórmanos
    -0.62
    Память
    -0.61
     klubben
    -0.61
    POSITIVE LOGITS
    templateUrl
    0.56
    by
    0.54
    AddTagHelper
    0.53
    src
    0.50
    Cer
    0.50
    Heres
    0.49
    OrBuilder
    0.48
    By
    0.48
     is
    0.48
     Here
    0.47
    Act Density 0.052%

    No Known Activations