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

    Neuronpedia

    INDEX
    Explanations

    mol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hist
    -0.06
     también
    -0.06
     wires
    -0.06
    windows
    -0.06
     ص
    -0.06
    ầm
    -0.06
     Telegram
    -0.06
    ued
    -0.06
     název
    -0.06
    seudo
    -0.06
    POSITIVE LOGITS
    ,col
    0.08
     granite
    0.07
    PACK
    0.07
     �
    0.06
    ۱۳۸
    0.06
    "(
    0.06
     一般
    0.06
     BH
    0.06
     må
    0.06
    _BP
    0.06
    Act Density 0.001%

    No Known Activations