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

    Neuronpedia

    INDEX
    Explanations

    reasons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Федерации
    -0.07
     החדשה
    -0.07
     가져
    -0.07
    といえば
    -0.07
     Lonely
    -0.07
    zw
    -0.07
    agascar
    -0.06
    /downloads
    -0.06
    可想
    -0.06
    玦
    -0.06
    POSITIVE LOGITS
     �
    0.08
    _attempt
    0.07
     sustain
    0.07
    .Pro
    0.07
    _De
    0.07
    contract
    0.07
     Palette
    0.07
     پ
    0.06
    الة
    0.06
    anut
    0.06
    Act Density 0.001%

    No Known Activations