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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gladly
    -0.07
    .xy
    -0.06
    Uuid
    -0.06
     arteries
    -0.06
    ี่
    -0.06
    aldo
    -0.06
                                                    ↵
    -0.06
    porte
    -0.06
    фер
    -0.06
     Gül
    -0.06
    POSITIVE LOGITS
     })}↵
    0.07
    ड़क
    0.06
    ]string
    0.06
     terra
    0.06
    raw
    0.06
     말을
    0.06
     explan
    0.06
     //=
    0.06
    RequestBody
    0.06
     Theodore
    0.06
    Act Density 0.003%

    No Known Activations