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

    Neuronpedia

    INDEX
    Explanations

    geared towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Personalized
    0.45
    Georg
    0.43
    для
    0.40
    Male
    0.40
    Barbara
    0.39
    Young
    0.39
    dear
    0.39
    Qualified
    0.38
    Mah
    0.38
     personalized
    0.38
    POSITIVE LOGITS
    向
    0.53
     نحو
    0.49
     wheels
    0.49
     hacia
    0.48
     towards
    0.47
     toward
    0.44
    beitet
    0.44
     seca
    0.41
    ointing
    0.41
     upto
    0.40
    Act Density 0.003%

    No Known Activations