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

    Neuronpedia

    INDEX
    Explanations

    CR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :r
    -0.07
     Psr
    -0.07
    毫
    -0.07
     �
    -0.07
    inz
    -0.06
     же
    -0.06
     outcomes
    -0.06
    _ch
    -0.06
     Kasich
    -0.06
    ra
    -0.06
    POSITIVE LOGITS
    TIMER
    0.08
    (pid
    0.06
    actable
    0.06
     tidy
    0.06
     Coronavirus
    0.06
    weekday
    0.06
     xmm
    0.06
     فرمود
    0.06
    징
    0.06
    /***
    0.06
    Act Density 0.015%

    No Known Activations