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

    Neuronpedia

    INDEX
    Explanations

    Contrasting statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     busy
    -0.07
    家伙
    -0.07
     spotlight
    -0.07
    okus
    -0.07
    áh
    -0.06
     simultaneous
    -0.06
     Fiat
    -0.06
     generado
    -0.06
    _Show
    -0.06
    ILD
    -0.06
    POSITIVE LOGITS
     cedar
    0.06
    ...)
    0.06
    :]↵↵
    0.06
     �
    0.06
    écial
    0.06
    لاة
    0.06
    710
    0.06
     Natalie
    0.06
    lte
    0.06
    Catalog
    0.06
    Act Density 0.033%

    No Known Activations