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

    Neuronpedia

    INDEX
    Explanations

    ===

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alarm
    -0.07
    글상위
    -0.06
    Japgolly
    -0.06
     الق
    -0.06
     equally
    -0.06
     στον
    -0.06
    kom
    -0.06
     worker
    -0.06
    <|python_tag|>
    -0.06
     councillors
    -0.06
    POSITIVE LOGITS
    Descripcion
    0.06
    nya
    0.06
     yavaş
    0.06
     Brow
    0.06
     fName
    0.06
     Minor
    0.06
    pered
    0.06
    avaş
    0.06
    arious
    0.06
    habi
    0.06
    Act Density 0.013%

    No Known Activations