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

    Neuronpedia

    INDEX
    Explanations

    terms related to parenting and family dynamics

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

    Following certain words

    np_acts-logits-general · gemini-2.0-flash

    define or explain things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Loves
    -0.62
    참고
    -0.57
    )();
    -0.55
    ')['
    -0.55
    وعة
    -0.55
     survives
    -0.55
    orku
    -0.54
    örn
    -0.54
     Exists
    -0.54
    Loves
    -0.54
    POSITIVE LOGITS
     means
    1.30
    means
    1.10
     isn
    1.02
     Means
    0.96
     MEANS
    0.95
    Means
    0.94
     vuol
    0.93
     wasn
    0.88
     yourself
    0.87
     berarti
    0.85
    Act Density 0.311%

    No Known Activations