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

    Neuronpedia

    INDEX
    Explanations

    Potential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jab
    -0.07
    -shot
    -0.07
     Mid
    -0.06
    NIL
    -0.06
    _pipeline
    -0.06
    нимать
    -0.06
     Lyons
    -0.06
    іг
    -0.06
    lista
    -0.06
    cpt
    -0.06
    POSITIVE LOGITS
    ]<
    0.07
     випадку
    0.06
    WindowState
    0.06
    コン
    0.06
    (reply
    0.06
     конс
    0.06
     точно
    0.06
     karşılık
    0.06
    以外
    0.06
    도
    0.06
    Act Density 0.086%

    No Known Activations