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

    Neuronpedia

    INDEX
    Explanations

    divide or multiply

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ?>">
    -0.10
     კონკრეტ
    -0.10
     რომელ
    -0.09
    σότε
    -0.09
     სავ
    -0.09
     ერთ
    -0.09
    怎么领
    -0.09
     οποίος
    -0.09
     რა
    -0.09
     քանի
    -0.09
    POSITIVE LOGITS
     accordingly
    0.16
    :↵↵
    0.12
    .↵↵
    0.12
     Accordingly
    0.10
     allí
    0.10
    ：↵↵
    0.09
     derfor
    0.09
    :↵
    0.09
     därför
    0.08
     :↵↵
    0.08
    Act Density 0.022%

    No Known Activations