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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages/places/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     misery
    -0.07
    民族
    -0.07
    _regularizer
    -0.07
    _TRA
    -0.06
    μένη
    -0.06
    toHaveBeenCalled
    -0.06
     Notifications
    -0.06
    したら
    -0.06
    भग
    -0.06
     راهنم
    -0.06
    POSITIVE LOGITS
     Cyril
    0.07
     courthouse
    0.07
     Gift
    0.06
    yre
    0.06
    -used
    0.06
     kış
    0.06
    átor
    0.06
     complexes
    0.06
     dear
    0.06
    	mysql
    0.06
    Act Density 0.001%

    No Known Activations