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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     keynote
    -0.07
     gor
    -0.06
     adventurous
    -0.06
     �
    -0.06
    cie
    -0.06
     cere
    -0.06
    _y
    -0.06
     attracts
    -0.06
    ALE
    -0.06
    POSITIVE LOGITS
     celebrations
    0.07
    handling
    0.06
    __('
    0.06
    golden
    0.06
    /repos
    0.06
    西省
    0.06
     assessed
    0.06
     principalTable
    0.06
    assword
    0.06
    .RESET
    0.06
    Act Density 0.025%

    No Known Activations