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

    Neuronpedia

    INDEX
    Explanations

    delta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kuvvet
    -0.07
     conditioned
    -0.06
     Div
    -0.06
     시간
    -0.06
    Marshal
    -0.06
     rival
    -0.05
     Clothes
    -0.05
     assertEquals
    -0.05
    blank
    -0.05
     dici
    -0.05
    POSITIVE LOGITS
    ajar
    0.07
    ....
    0.07
    Ease
    0.07
    nesc
    0.07
    ünst
    0.07
     Alliance
    0.07
    onom
    0.07
    ยง
    0.07
    ancy
    0.06
    →→
    0.06
    Act Density 0.008%

    No Known Activations