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

    Neuronpedia

    INDEX
    Explanations

    future outcomes and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Its
    0.61
     Lena
    0.61
     Your
    0.59
    记住
    0.59
     S
    0.55
     You
    0.54
    know
    0.54
     Often
    0.54
     Thinking
    0.54
     Fitness
    0.53
    POSITIVE LOGITS
     candidacy
    0.65
     addirittura
    0.65
     assassination
    0.63
     candidatura
    0.62
     আদৌ
    0.61
     imminent
    0.61
     assass
    0.58
     spying
    0.57
     misog
    0.56
     elec
    0.55
    Act Density 0.142%

    No Known Activations