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

    Neuronpedia

    INDEX
    Explanations

    straight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帐
    -0.08
    总
    -0.08
    .box
    -0.08
     case
    -0.08
    .?
    -0.08
    �
    -0.07
    umn
    -0.07
    恰好
    -0.07
    �
    -0.07
    :$
    -0.07
    POSITIVE LOGITS
     sane
    0.09
     Montana
    0.08
     découvert
    0.08
    骈
    0.08
     الجديد
    0.07
     Straight
    0.07
     straight
    0.07
     datatype
    0.07
     storyline
    0.07
     verwendet
    0.07
    Act Density 0.009%

    No Known Activations