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

    Neuronpedia

    INDEX
    Explanations

    Inhibiting breakdown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affirmation
    -0.07
    CONNECT
    -0.07
     naming
    -0.07
     Ferrari
    -0.07
    label
    -0.06
    fila
    -0.06
     '''
    -0.06
    erse
    -0.06
    endi
    -0.06
    cad
    -0.06
    POSITIVE LOGITS
     الإن
    0.07
     CTL
    0.07
     густ
    0.06
    _boundary
    0.06
     ++$
    0.06
     अपर
    0.06
     جنگ
    0.06
     ParameterDirection
    0.06
     glac
    0.06
    (lines
    0.06
    Act Density 0.114%

    No Known Activations