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

    Neuronpedia

    INDEX
    Explanations

    elements related to communication and their technical specifications

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

    names and skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.73
    сылкі
    -0.66
    featureID
    -0.64
     <<<<<<<<<<<<<<
    -0.60
    WireFormatLite
    -0.60
     nonUne
    -0.60
     AttributeSet
    -0.58
    transQ
    -0.57
    ThroughAttribute
    -0.57
    __(/*!
    -0.55
    POSITIVE LOGITS
     named
    0.65
    Personendaten
    0.57
     names
    0.55
     name
    0.54
     Namens
    0.50
    Named
    0.49
     renamed
    0.49
     bernama
    0.48
     Named
    0.48
     namens
    0.48
    Act Density 0.070%

    No Known Activations