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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sport
    -0.08
     Rescue
    -0.07
    鸰
    -0.07
     מהמ
    -0.07
    undi
    -0.07
     urine
    -0.07
     Ambassador
    -0.07
    女士
    -0.07
    Jane
    -0.07
    ʇ
    -0.07
    POSITIVE LOGITS
     realizing
    0.08
    _season
    0.07
     الش
    0.07
     modes
    0.07
    栝
    0.07
    先进
    0.06
    .row
    0.06
     assumes
    0.06
    	mod
    0.06
    멤
    0.06
    Act Density 0.000%

    No Known Activations