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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tween
    -0.07
    .the
    -0.07
    ्ल
    -0.07
    ात
    -0.07
     cuisine
    -0.06
     Section
    -0.06
     bfd
    -0.06
     změn
    -0.06
     sped
    -0.06
    Nuevo
    -0.06
    POSITIVE LOGITS
     プロ
    0.08
     Εθν
    0.08
    _that
    0.07
    贝
    0.06
    仔
    0.06
    ucher
    0.06
    fel
    0.06
     Sır
    0.06
    selectorMethod
    0.06
     nag
    0.06
    Act Density 0.000%

    No Known Activations