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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lighting
    -0.06
    018
    -0.06
     mover
    -0.06
     hoop
    -0.06
     movers
    -0.06
     Lime
    -0.06
     rivers
    -0.06
    添加
    -0.06
     též
    -0.06
     教
    -0.06
    POSITIVE LOGITS
    =random
    0.07
    خ
    0.07
     область
    0.07
    .BooleanField
    0.07
     GameObject
    0.06
     paramet
    0.06
     ox
    0.06
    experimental
    0.06
     nisi
    0.06
    amil
    0.06
    Act Density 0.024%

    No Known Activations