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

    Neuronpedia

    INDEX
    Explanations

    pl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @@
    -0.07
    涂层
    -0.07
    IDS
    -0.07
    itur
    -0.07
    泡泡
    -0.06
     tense
    -0.06
    气候
    -0.06
     Crop
    -0.06
     ISIL
    -0.06
    Tau
    -0.06
    POSITIVE LOGITS
    WARDED
    0.07
    نصوص
    0.07
    IRM
    0.07
    vrir
    0.07
    朸
    0.07
    window
    0.06
     objections
    0.06
    _checkbox
    0.06
    licken
    0.06
    ৡ
    0.06
    Act Density 0.000%

    No Known Activations