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

    Neuronpedia

    INDEX
    Explanations

    Access Modifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =").
    -0.07
    _goods
    -0.07
    нике
    -0.06
    声音
    -0.06
    _wheel
    -0.06
    moduleName
    -0.06
     LAND
    -0.06
    κό
    -0.06
    mand
    -0.06
     здесь
    -0.06
    POSITIVE LOGITS
    -score
    0.07
    ści
    0.06
     нарез
    0.06
     Int
    0.06
     Parts
    0.06
    stry
    0.06
    vably
    0.06
    plets
    0.06
     چیزی
    0.06
    (pt
    0.06
    Act Density 0.141%

    No Known Activations