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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Returning
    -0.08
    眼中
    -0.07
    .getLong
    -0.07
    随手
    -0.07
    _printer
    -0.07
    云
    -0.07
    �
    -0.07
     Ends
    -0.07
    𬜯
    -0.07
     Parents
    -0.07
    POSITIVE LOGITS
     heterosexual
    0.07
    幽默
    0.07
     outrageous
    0.07
    地震
    0.07
     battle
    0.06
    vement
    0.06
    flatten
    0.06
     Minority
    0.06
     لأن
    0.06
    	system
    0.06
    Act Density 0.001%

    No Known Activations