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

    Neuronpedia

    INDEX
    Explanations

    physics and movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Runner
    -0.07
     retval
    -0.07
    فئة
    -0.07
     Poetry
    -0.07
    !;↵
    -0.06
    ignored
    -0.06
    	damage
    -0.06
     Mans
    -0.06
    解决问题
    -0.06
     ريال
    -0.06
    POSITIVE LOGITS
    专利
    0.08
    bz
    0.07
    _process
    0.07
     preservation
    0.07
    फ
    0.07
    パ
    0.06
     الط
    0.06
    .val
    0.06
    ﺻ
    0.06
    .Stage
    0.06
    Act Density 0.098%

    No Known Activations