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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    achable
    0.37
     Touchable
    0.35
    (`
    0.35
     методом
    0.34
    üle
    0.34
    これは
    0.33
    $"
    0.32
     Fairchild
    0.32
    (!
    0.32
     ``
    0.31
    POSITIVE LOGITS
     bioqu
    0.38
     chap
    0.38
    PTV
    0.36
     sommer
    0.35
    Especific
    0.35
     sév
    0.35
    CONFIGURE
    0.34
    тник
    0.34
     विभागों
    0.34
     Physic
    0.34
    Act Density 0.040%

    No Known Activations