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
     precipitation
    -0.06
    _SWITCH
    -0.06
     Accident
    -0.06
     Leadership
    -0.06
     pavement
    -0.06
     glamour
    -0.06
     pump
    -0.06
     slice
    -0.06
     Pump
    -0.06
     LENG
    -0.06
    POSITIVE LOGITS
     Hindered
    0.07
     आव
    0.07
     freeing
    0.07
    ص
    0.07
    еної
    0.06
    Transition
    0.06
    .div
    0.06
    説明
    0.06
     hemp
    0.06
    sx
    0.06
    Act Density 0.022%

    No Known Activations