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

    Neuronpedia

    INDEX
    Explanations

    references to processes and relationships in various contexts

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

    Follows question words (how, what, why)

    np_acts-logits-general · gemini-2.0-flash

    how or what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromCharCode
    -0.56
    بوابة
    -0.55
    Portale
    -0.53
    rophes
    -0.51
    radura
    -0.50
    Приятного
    -0.49
     zosta
    -0.47
    warten
    -0.47
    Tikang
    -0.46
     resourceCulture
    -0.46
    POSITIVE LOGITS
     how
    1.27
    how
    0.95
     cómo
    0.95
     why
    0.89
     "..\..\..\
    0.82
     what
    0.78
     bagaimana
    0.78
     ways
    0.75
    cómo
    0.72
    ]")]
    0.71
    Act Density 0.311%

    No Known Activations