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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Retail
    -0.07
     MsgBox
    -0.06
    Channel
    -0.06
     숨
    -0.06
     Arrays
    -0.06
     ability
    -0.06
    $h
    -0.06
     ib
    -0.06
     Education
    -0.06
     nails
    -0.06
    POSITIVE LOGITS
    ührung
    0.07
     IsPlainOldData
    0.06
    acağız
    0.06
    eceğiz
    0.06
    ueue
    0.06
     defeats
    0.06
    _cache
    0.06
     بإ
    0.06
    каз
    0.06
    vinc
    0.06
    Act Density 0.069%

    No Known Activations