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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cancel
    -0.08
    oct
    -0.07
    _EDITOR
    -0.07
     validating
    -0.07
     houses
    -0.07
     patch
    -0.07
    jos
    -0.07
    vang
    -0.07
     Dol
    -0.07
     operator
    -0.07
    POSITIVE LOGITS
     تصمیم
    0.07
    оны
    0.06
    _TR
    0.06
    	move
    0.06
    )){
↵
    0.06
    _LOG
    0.06
    IMIZE
    0.06
    isko
    0.06
    ภายใน
    0.06
    _ME
    0.06
    Act Density 0.024%

    No Known Activations