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

    Neuronpedia

    INDEX
    Explanations

    eslint and code style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কলার
    1.26
    сти
    1.23
     dilated
    1.17
     stubbornly
    1.17
    స్
    1.15
    setFooter
    1.15
    댈
    1.13
     absorbers
    1.13
    getCameraId
    1.10
     Stereo
    1.10
    POSITIVE LOGITS
    ν
    1.81
    fos
    1.47
    動き
    1.36
    fes
    1.36
    gestion
    1.35
     gne
    1.34
    Honestly
    1.33
    valores
    1.32
    enne
    1.32
     unre
    1.30
    Act Density 0.001%

    No Known Activations