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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ninth
    -0.07
     Pipes
    -0.07
     precondition
    -0.06
    lose
    -0.06
     Fre
    -0.06
     Woo
    -0.06
     retal
    -0.06
    	debug
    -0.06
     thought
    -0.06
     Total
    -0.06
    POSITIVE LOGITS
    ्ण
    0.07
    AILS
    0.06
    swift
    0.06
    sz
    0.06
     arr
    0.06
     Şubat
    0.06
    ाजन
    0.06
    ImageSharp
    0.06
    ンパ
    0.06
    átka
    0.05
    Act Density 0.002%

    No Known Activations