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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning or giving advice

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

    Non-English text or code snippets

    np_acts-logits-general · gemini-2.0-flash

    foreign languages and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kt
    -0.51
     zostały
    -0.44
     christ
    -0.43
    Sherry
    -0.42
    isLoaded
    -0.42
     TAMBIÉN
    -0.41
    thor
    -0.40
    lif
    -0.40
     shalt
    -0.40
    skosten
    -0.40
    POSITIVE LOGITS
    intios
    0.73
     Normdatei
    0.71
    endphp
    0.68
     autorytatywna
    0.67
     disponibilités
    0.66
    WebElementEntity
    0.65
    onAttach
    0.60
    حياته
    0.60
    itemBuilder
    0.59
    })();
    0.58
    Act Density 0.037%

    No Known Activations