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

    Neuronpedia

    INDEX
    Explanations

    Math word problems with rates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waya
    -0.08
    Attached
    -0.07
    usp
    -0.07
     interpreter
    -0.07
    Instantiate
    -0.07
     richer
    -0.07
    Swap
    -0.07
    Move
    -0.07
    Attachment
    -0.07
    ্কার
    -0.07
    POSITIVE LOGITS
     Dados
    0.09
     الواحد
    0.09
     നിര
    0.09
    മുള്ള
    0.09
    Todas
    0.09
     hábito
    0.08
    （月
    0.08
     inteira
    0.08
     habituales
    0.08
     طوال
    0.08
    Act Density 0.029%

    No Known Activations