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

    Neuronpedia

    INDEX
    Explanations

    HTML input types and attributes

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

    input type attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.95
    AndEndTag
    -0.90
    IntoConstraints
    -0.84
    niſſe
    -0.82
     Geſch
    -0.81
     queſta
    -0.80
     مرئيه
    -0.79
    <unused74>
    -0.79
    <pad>
    -0.79
    <unused23>
    -0.79
    POSITIVE LOGITS
    inputType
    0.39
    type
    0.36
     type
    0.36
    keyboardType
    0.31
     tipo
    0.28
     тип
    0.27
    TYPE
    0.24
    ASX
    0.23
    sourceType
    0.23
     tipe
    0.23
    Act Density 0.010%

    No Known Activations