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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	comment
    -0.07
    compiled
    -0.06
    费用
    -0.06
    _clip
    -0.06
     killers
    -0.06
    /form
    -0.06
     боли
    -0.06
     nád
    -0.06
     priority
    -0.06
     Comics
    -0.06
    POSITIVE LOGITS
     turquoise
    0.07
     olup
    0.07
    (Line
    0.07
     wyst
    0.07
    Angel
    0.06
     schn
    0.06
    apus
    0.06
    *:
    0.06
     جز
    0.06
     можна
    0.06
    Act Density 0.013%

    No Known Activations