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

    Neuronpedia

    INDEX
    Explanations

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igne
    -0.08
    _[
    -0.07
    Navig
    -0.07
    Consumer
    -0.07
    群里
    -0.07
     grandson
    -0.07
     learning
    -0.07
    .getSharedPreferences
    -0.07
    =>
    -0.07
    Defense
    -0.07
    POSITIVE LOGITS
     violate
    0.07
    นโย
    0.06
    עביר
    0.06
     mdl
    0.06
    𝗥
    0.06
    不超过
    0.06
     kur
    0.06
     okreś
    0.06
     correct
    0.06
    熵
    0.06
    Act Density 0.010%

    No Known Activations