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

    Neuronpedia

    INDEX
    Explanations

    words related to the act of discussing or sharing information

    oai_token-act-pair · gemini-2.0-flash

    words related to discussion and dialogue

    np_token-act-pair-logits · gpt-4o-mini

    discussing, examining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    for
    -0.49
    with
    -0.46
    or
    -0.46
     continúas
    -0.45
    up
    -0.45
    p
    -0.44
    they
    -0.44
    pl
    -0.44
     сравнению
    -0.44
    from
    -0.43
    POSITIVE LOGITS
     how
    1.23
    MigrationBuilder
    0.87
     cómo
    0.81
     ways
    0.79
     why
    0.79
     HOW
    0.75
     कैसे
    0.75
    how
    0.74
    __':
    0.74
    GraphicsUnit
    0.73
    Act Density 3.840%

    No Known Activations