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

    Neuronpedia

    INDEX
    Explanations

    opaque types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    -3.47
     was
    -3.17
    ar
    -2.88
    d
    -2.88
     has
    -2.81
     *
    -2.56
     "
    -2.53
     You
    -2.42
    a
    -2.38
     )
    -2.34
    POSITIVE LOGITS
     diki
    2.67
    镚
    2.61
     kollu
    2.56
    Ꮉ
    2.56
    selben
    2.50
    憮
    2.50
     清新
    2.42
     kopling
    2.39
    秕
    2.39
     triko
    2.36
    Act Density 0.007%

    No Known Activations