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

    Neuronpedia

    INDEX
    Explanations

    elements related to competition and rankings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparing winning, titles, or advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.63
     sahiptir
    -0.59
     betweenstory
    -0.59
    StoryboardSegue
    -0.54
     ब्रेकडाउन
    -0.53
    Personendaten
    -0.49
     Roskov
    -0.49
    Filmografia
    -0.48
     magnético
    -0.47
     gevolg
    -0.47
    POSITIVE LOGITS
    virgin
    0.39
     Stock
    0.39
    umerable
    0.38
     Ny
    0.38
     Pep
    0.37
     Virgin
    0.37
     anton
    0.36
     Widow
    0.35
    }^{+}\
    0.35
     unlimited
    0.35
    Act Density 0.160%

    No Known Activations