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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inconvenience
    -0.08
     extrema
    -0.08
     encountered
    -0.08
     inconvenient
    -0.08
    Taken
    -0.08
     surpre
    -0.08
     Callable
    -0.08
    Callable
    -0.08
    Feel
    -0.08
     sorpr
    -0.07
    POSITIVE LOGITS
     활성
    0.09
     enabling
    0.09
    enzione
    0.08
     transistor
    0.08
    -enable
    0.08
    _ENABLE
    0.08
    .enable
    0.08
    开启
    0.08
    _Enable
    0.08
    fullscreen
    0.08
    Act Density 0.002%

    No Known Activations