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

    Neuronpedia

    INDEX
    Explanations

    scientific citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    电
    -0.08
     CI
    -0.08
     Ci
    -0.08
     ice
    -0.08
    uite
    -0.07
     Lee
    -0.07
    火
    -0.07
    CI
    -0.07
    xygen
    -0.07
     yi
    -0.07
    POSITIVE LOGITS
    9
    0.14
    19
    0.09
    159
    0.08
    189
    0.08
     九
    0.08
     September
    0.08
    09
    0.08
    179
    0.08
     Nine
    0.08
    109
    0.08
    Act Density 0.232%

    No Known Activations