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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IFIED
    -0.07
    ریه
    -0.07
    aim
    -0.07
     Muk
    -0.07
    AUTH
    -0.06
    iles
    -0.06
     judges
    -0.06
    řit
    -0.06
    oute
    -0.06
    ánh
    -0.06
    POSITIVE LOGITS
    >').
    0.07
    ServiceImpl
    0.07
    /car
    0.06
     Ivan
    0.06
     discontin
    0.06
     mutating
    0.06
    esy
    0.06
    ("----------------
    0.06
     shut
    0.06
     documenting
    0.06
    Act Density 0.006%

    No Known Activations