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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GY
    -0.07
    RI
    -0.07
    .defaults
    -0.07
     일어
    -0.07
     mie
    -0.07
    这种
    -0.06
     unmistak
    -0.06
     sớm
    -0.06
     JNIEnv
    -0.06
     Elegant
    -0.06
    POSITIVE LOGITS
    /Sub
    0.06
     التح
    0.06
    ])-
    0.06
    .Interop
    0.06
     Fib
    0.05
     Loop
    0.05
     informací
    0.05
    .An
    0.05
     imprimir
    0.05
    _nav
    0.05
    Act Density 0.003%

    No Known Activations