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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finger
    -0.07
    νομ
    -0.06
     downs
    -0.06
    Hen
    -0.06
     sue
    -0.06
     communicating
    -0.06
     narcotics
    -0.06
     ج
    -0.06
     rever
    -0.06
     Vehicles
    -0.06
    POSITIVE LOGITS
    Amt
    0.07
     saber
    0.07
    _REMOTE
    0.06
    ตำบล
    0.06
     aboard
    0.06
    �
    0.06
     nécessaire
    0.06
    之后
    0.06
     Льв
    0.06
    ------↵↵
    0.06
    Act Density 0.042%

    No Known Activations