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

    Neuronpedia

    INDEX
    Explanations

    bowl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Mod
    -0.07
    	stat
    -0.07
     serif
    -0.07
    庠
    -0.07
     עוד
    -0.06
    amil
    -0.06
    تجاوز
    -0.06
    monitor
    -0.06
    .Fire
    -0.06
     Crafts
    -0.06
    POSITIVE LOGITS
     qualified
    0.07
    _call
    0.07
     SIMPLE
    0.07
     assuming
    0.07
    停止
    0.07
    .Auto
    0.07
    商家
    0.07
    模式
    0.07
    _FWD
    0.07
    .annotation
    0.07
    Act Density 0.003%

    No Known Activations