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

    Neuronpedia

    INDEX
    Explanations

    structured lists or sequences

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

    a number in parentheses

    np_acts-logits-general · gemini-2.0-flash

    enumerating lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.72
    ]--;
    -0.72
     estimés
    -0.70
    expandindo
    -0.65
    Véxase
    -0.65
    TestBed
    -0.62
     deepcopy
    -0.62
     Waray
    -0.60
     ECM
    -0.59
    __((
    -0.59
    POSITIVE LOGITS
    liputi
    0.48
     fatti
    0.48
    στα
    0.48
    pielt
    0.46
    WORTH
    0.45
     Vordergrund
    0.44
    lloworld
    0.44
     First
    0.44
    phate
    0.43
    zków
    0.43
    Act Density 0.195%

    No Known Activations