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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <System
    -0.07
     pandemic
    -0.06
    ыџN
    -0.06
    พบ
    -0.06
     дает
    -0.06
    oward
    -0.06
    .Cor
    -0.06
    oplayer
    -0.06
    _THRESHOLD
    -0.05
    opolitan
    -0.05
    POSITIVE LOGITS
     bearings
    0.07
    ategorical
    0.07
     ERR
    0.07
     attributes
    0.07
     related
    0.06
     gerekmektedir
    0.06
    _handler
    0.06
    <!--
    0.06
    Ast
    0.06
     без
    0.06
    Act Density 0.002%

    No Known Activations