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

    Neuronpedia

    INDEX
    Explanations

    references to programming libraries or modules

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

    domain prefixes and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pă
    -0.40
     boste
    -0.39
     rallado
    -0.35
    ējās
    -0.35
     Kategor
    -0.34
     orgánico
    -0.33
     contemporáneo
    -0.33
     cálido
    -0.33
     diría
    -0.33
    șe
    -0.32
    POSITIVE LOGITS
     FontWeight
    0.73
    httphttps
    0.69
    ྑ
    0.67
    ſammen
    0.65
     ſei
    0.63
    ๬
    0.63
    ⪜
    0.61
     wireType
    0.59
     ddelwed
    0.59
     Ain
    0.59
    Act Density 0.003%

    No Known Activations