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

    Neuronpedia

    INDEX
    Explanations

    references to personal comfort and understanding in writing

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

    Tokens after "Q" or "recommend"

    np_acts-logits-general · gemini-2.0-flash

    homework tutors assurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.63
    WebVitals
    -0.60
     provinciale
    -0.58
     negociación
    -0.55
     légitime
    -0.55
     kaynağından
    -0.54
     étrang
    -0.54
    rícula
    -0.54
     Introducing
    -0.54
     shameless
    -0.54
    POSITIVE LOGITS
    httphttps
    0.66
    )");
    0.58
    moiselle
    0.58
     كومونز
    0.54
    SPJ
    0.54
    躇
    0.54
    ))));
    0.52
     LUMP
    0.52
    )";
    0.52
     Kj
    0.52
    Act Density 0.022%

    No Known Activations