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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Es
    -0.08
     지방
    -0.07
     scientific
    -0.06
     strategic
    -0.06
    ajas
    -0.06
     hexadecimal
    -0.06
     sinister
    -0.06
    _x
    -0.06
    adecimal
    -0.06
    -tier
    -0.06
    POSITIVE LOGITS
     (!$
    0.06
    lude
    0.06
     EOF
    0.06
     histo
    0.06
    etre
    0.06
    pered
    0.06
    #$
    0.06
     criticised
    0.06
    archives
    0.06
     Bashar
    0.06
    Act Density 0.033%

    No Known Activations