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

    Neuronpedia

    INDEX
    Explanations

    including

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    のような
    -0.07
     Sphere
    -0.07
    )(*
    -0.06
    tra
    -0.06
    獲
    -0.06
     journalistic
    -0.06
     такі
    -0.06
    as
    -0.06
     realizar
    -0.06
     Zug
    -0.06
    POSITIVE LOGITS
     including
    0.09
     değil
    0.07
     percent
    0.07
    ntl
    0.06
    essel
    0.06
     validationResult
    0.06
    イヤ
    0.06
     noon
    0.06
    warning
    0.06
    िजन
    0.06
    Act Density 0.047%

    No Known Activations