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

    Neuronpedia

    INDEX
    Explanations

    references to accountability and criticism in a variety of contexts

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

    Reasons or causes for something

    np_acts-logits-general · gemini-2.0-flash

    something to vote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.58
     ſche
    -0.56
     Bantu
    -0.55
     poffible
    -0.53
     Jefus
    -0.52
     monographs
    -0.51
     ingrat
    -0.51
     Filho
    -0.50
     Tinto
    -0.50
     Bohemian
    -0.50
    POSITIVE LOGITS
     orgullo
    0.78
     orgull
    0.72
     proud
    0.72
     motivo
    0.72
     đáng
    0.72
     réjou
    0.71
     cause
    0.68
     pride
    0.66
     worthy
    0.63
     raisons
    0.63
    Act Density 0.120%

    No Known Activations