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

    Neuronpedia

    INDEX
    Explanations

    words related to forms requesting personal information

    oai_token-act-pair · gemini-2.0-flash

    phone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IBarButtonItem
    -0.52
    op
    -0.50
    est
    -0.47
     Mc
    -0.47
     meg
    -0.46
     –
    -0.45
     
    -0.45
     fine
    -0.44
     the
    -0.44
    VINCE
    -0.44
    POSITIVE LOGITS
     Majefty
    0.89
     itſelf
    0.82
     houſe
    0.80
    SequentialGroup
    0.80
     againſt
    0.80
     themſelves
    0.79
     ſtre
    0.78
     chofe
    0.77
     raiſ
    0.77
     ſeveral
    0.77
    Act Density 0.456%

    No Known Activations