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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DataTable
    -0.08
     compassionate
    -0.07
     PureComponent
    -0.07
     disbelief
    -0.07
     Pou
    -0.06
    .OrderBy
    -0.06
     dual
    -0.06
     бюдж
    -0.06
    amphetamine
    -0.06
    shader
    -0.06
    POSITIVE LOGITS
    стер
    0.07
    ję
    0.07
    cope
    0.06
    ()>
    0.06
     komple
    0.06
    /em
    0.06
     beginners
    0.06
    γράφ
    0.06
     انگ
    0.06
    über
    0.06
    Act Density 0.000%

    No Known Activations