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

    Neuronpedia

    INDEX
    Explanations

    specific person names or surnames

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

    names with accents or special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.60
    Jeografia
    -0.47
     GenerationType
    -0.42
    dafx
    -0.42
    yntaxException
    -0.42
    Portale
    -0.41
    zzá
    -0.41
    eston
    -0.40
    intios
    -0.40
     autorytatywna
    -0.39
    POSITIVE LOGITS
     zufolge
    0.51
    principalColumn
    0.43
    Obrázky
    0.40
     gefällt
    0.39
     femenina
    0.39
     boyunca
    0.38
    cipit
    0.38
    ッケージ
    0.38
     swoją
    0.37
    andExpect
    0.37
    Act Density 0.128%

    No Known Activations