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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    최
    -0.07
     yukarı
    -0.07
     mosques
    -0.07
    .Rows
    -0.06
    medicine
    -0.06
     neuen
    -0.06
    ُم
    -0.06
     otro
    -0.06
    廠
    -0.06
    avour
    -0.06
    POSITIVE LOGITS
     Ha
    0.07
    	entry
    0.07
    Ha
    0.07
    (),↵
    0.07
    181
    0.06
    Imp
    0.06
    	k
    0.06
     playlist
    0.06
    	Vec
    0.06
    (symbol
    0.06
    Act Density 0.000%

    No Known Activations