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
     territories
    -0.07
     Infinite
    -0.07
    _platform
    -0.07
    _factors
    -0.06
     Гар
    -0.06
    Realm
    -0.06
    つけ
    -0.06
    wards
    -0.06
     portals
    -0.06
     иск
    -0.06
    POSITIVE LOGITS
    _pop
    0.07
     BOOL
    0.07
     tournament
    0.06
     �
    0.06
    culator
    0.06
    COL
    0.06
     Beit
    0.06
    ológ
    0.06
     NA
    0.06
    doctor
    0.06
    Act Density 0.004%

    No Known Activations