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

    Neuronpedia

    INDEX
    Explanations

    code/internet snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sticks
    -0.07
    اک
    -0.07
    implified
    -0.07
     mostrar
    -0.06
     moet
    -0.06
     Santo
    -0.06
    _ES
    -0.06
    ournée
    -0.06
     livro
    -0.06
     Robert
    -0.06
    POSITIVE LOGITS
    पर
    0.07
     ObjectOutputStream
    0.07
    _ATOMIC
    0.07
    ลำ
    0.07
    bdb
    0.06
    ､_
    0.06
    getClass
    0.06
     дорож
    0.06
    ρευ
    0.06
    (Mat
    0.06
    Act Density 0.001%

    No Known Activations