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

    Neuronpedia

    INDEX
    Explanations

    phrases about limitations or knowledge, often including "as far as I know/can see" or mentioning options

    oai_token-act-pair · gemini-2.0-flash

    Expressing an opinion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.77
    InstanceState
    -0.63
    談社
    -0.61
    ICOLON
    -0.60
    RenderAtEndOf
    -0.59
    Rujuakan
    -0.57
    SequentialGroup
    -0.56
     doInBackground
    -0.56
    WriteAttribute
    -0.54
     Administrativna
    -0.54
    POSITIVE LOGITS
    
    0.69
    تص
    0.50
    Ety
    0.43
     \%$\\
    0.42
    蜂
    0.42
     anthropologists
    0.41
    وائد
    0.41
    治安
    0.41
    fxml
    0.41
     موض
    0.41
    Act Density 0.601%

    No Known Activations