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

    Neuronpedia

    INDEX
    Explanations

    Old

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     King
    -0.07
    /key
    -0.07
     cloning
    -0.07
     střed
    -0.06
    hid
    -0.06
    ing
    -0.06
    ments
    -0.06
    	spin
    -0.06
    King
    -0.06
     Lange
    -0.06
    POSITIVE LOGITS
     στον
    0.06
     título
    0.06
     اطل
    0.06
     venda
    0.06
    Feat
    0.06
    .compile
    0.06
     FEATURE
    0.06
     거야
    0.05
     Composer
    0.05
     questionable
    0.05
    Act Density 0.248%

    No Known Activations