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

    Neuronpedia

    INDEX
    Explanations

    management and reporting structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ទេ។
    0.42
     и
    0.41
     आणि
    0.40
    विषयी
    0.39
     અને
    0.39
    하지
    0.39
     և
    0.38
    𝗆
    0.38
    ören
    0.36
     and
    0.36
    POSITIVE LOGITS
     combo
    0.38
    分别是
    0.38
    都需要
    0.36
     Combo
    0.36
     arasındaki
    0.36
    相结合
    0.36
     juntos
    0.35
     hurdles
    0.35
     Mars
    0.34
     একসাথে
    0.33
    Act Density 0.181%

    No Known Activations