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

    Neuronpedia

    INDEX
    Explanations

    Authentication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wording
    -0.06
     wom
    -0.06
    ocities
    -0.06
     далеко
    -0.06
     conception
    -0.06
     trained
    -0.06
    EDIATEK
    -0.06
     frees
    -0.06
    ovaly
    -0.06
    flags
    -0.06
    POSITIVE LOGITS
     возник
    0.07
     serge
    0.07
    _STORAGE
    0.07
     Kanun
    0.06
     sprinkle
    0.06
     kazan
    0.06
    _EXPORT
    0.06
    _VM
    0.06
    (enc
    0.06
     입
    0.06
    Act Density 0.034%

    No Known Activations