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

    Neuronpedia

    INDEX
    Explanations

    always willing to do whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Denne
    0.57
    Esse
    0.54
    铖
    0.50
    Este
    0.48
     nessuna
    0.48
    Па
    0.45
    Altri
    0.45
    વતી
    0.45
    Panoramic
    0.44
    ړئ
    0.44
    POSITIVE LOGITS
     Reproduced
    0.50
     reproduce
    0.49
    aniyati
    0.47
     reproduc
    0.46
     follow
    0.44
     reproduced
    0.44
    __':
    0.40
     Politik
    0.40
     Reprodu
    0.40
     try
    0.40
    Act Density 0.004%

    No Known Activations