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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" and various equality operations

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

    user and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nezeu
    -0.63
    parsedMessage
    -0.62
    Personendaten
    -0.60
    featureID
    -0.59
     TextInputType
    -0.57
    áctenos
    -0.55
    findpost
    -0.54
    verifyException
    -0.54
    WireFormatLite
    -0.53
    webElementXpaths
    -0.53
    POSITIVE LOGITS
     bad
    0.45
     inf
    0.44
     mail
    0.41
    CharSequence
    0.40
    bad
    0.39
    ac
    0.39
    HasColumnType
    0.39
    fig
    0.38
     ev
    0.38
     fig
    0.38
    Act Density 0.007%

    No Known Activations