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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ทา
    -0.09
    .con
    -0.08
    𝕴
    -0.07
    ☿
    -0.07
    .Keys
    -0.07
     iv
    -0.07
    .kode
    -0.07
    开支
    -0.07
    .transparent
    -0.07
    _menu
    -0.07
    POSITIVE LOGITS
    ayan
    0.08
    atin
    0.07
     restaur
    0.07
     Earn
    0.07
     celebrating
    0.07
    Chuck
    0.07
     flex
    0.07
    :j
    0.07
    фин
    0.07
     finding
    0.06
    Act Density 0.002%

    No Known Activations