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

    Neuronpedia

    INDEX
    Explanations

    references to burdens and responsibilities

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

    abstract nouns

    np_acts-logits-general · gemini-2.0-flash

    personal concepts and abstractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.84
    %");
    -0.75
    */;
    -0.65
    ']
    -0.65
    %";
    -0.63
    ()");
    -0.63
    providedIn
    -0.62
    )':
    -0.61
    AutoresizingMask
    -0.61
    "):
    -0.61
    POSITIVE LOGITS
    +#+#
    0.64
    DebuggerNonUser
    0.55
    COUVER
    0.52
     שוליים
    0.52
    UnusedPrivate
    0.48
    rrggbb
    0.47
     للمعارف
    0.47
    LabelTagHelper
    0.46
     accompli
    0.46
    WriteTagHelper
    0.45
    Act Density 0.606%

    No Known Activations