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

    Neuronpedia

    INDEX
    Explanations

    being subjected to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caracteres
    0.75
     domination
    0.65
     atrocious
    0.65
     malicious
    0.63
     miraculous
    0.63
     justification
    0.62
     undesirable
    0.62
     fazem
    0.61
     decorative
    0.61
     likelihood
    0.61
    POSITIVE LOGITS
    看到
    0.73
    Voir
    0.68
    如此
    0.64
    可以看到
    0.64
    Sam
    0.64
    Being
    0.63
    ég
    0.63
     иметь
    0.63
    avoir
    0.62
     seeing
    0.61
    Act Density 0.096%

    No Known Activations