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

    Neuronpedia

    INDEX
    Explanations

    like a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    髖
    0.43
    禊
    0.41
     defec
    0.40
     bodily
    0.38
     गिफ्ट
    0.38
    ્ઞ
    0.38
     renormal
    0.38
    веро
    0.36
    ificante
    0.36
     Hb
    0.35
    POSITIVE LOGITS
     idiot
    0.63
     rabbits
    0.62
     fools
    0.62
     zombies
    0.61
     idiots
    0.61
     animals
    0.60
     zombie
    0.57
     fool
    0.57
     reptiles
    0.57
     sponges
    0.55
    Act Density 0.086%

    No Known Activations