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

    Neuronpedia

    INDEX
    Explanations

    references to individual agency and personal responsibility

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

    following pronouns

    np_acts-logits-general · gemini-2.0-flash

    better than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    جغرافيا
    -0.66
     Dadurch
    -0.49
    RenderAtEndOf
    -0.47
    AndEndTag
    -0.43
    Географи
    -0.41
    يكا
    -0.40
    extAlignment
    -0.39
    addCriterion
    -0.39
     lagi
    -0.38
    thâu
    -0.38
    POSITIVE LOGITS
     better
    2.97
    better
    2.76
    Better
    2.56
     Better
    2.47
     BETTER
    2.23
     mejor
    2.05
     melhor
    2.02
     meglio
    1.99
     besser
    1.98
     mieux
    1.92
    Act Density 0.270%

    No Known Activations