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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	TokenName
    -0.07
    高度
    -0.07
    _TOKEN
    -0.07
    쯤
    -0.07
    נו
    -0.07
     Added
    -0.07
    _fraction
    -0.07
    	Title
    -0.07
    �性
    -0.06
    젠
    -0.06
    POSITIVE LOGITS
     payout
    0.08
     moderation
    0.08
     failing
    0.07
     att
    0.07
     reife
    0.07
     ausge
    0.07
    擊
    0.07
     po
    0.07
    饮用水
    0.06
     ctypes
    0.06
    Act Density 0.009%

    No Known Activations