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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SPA
    -0.08
     olumlu
    -0.07
     FM
    -0.07
     Поч
    -0.07
    .route
    -0.07
     zn
    -0.07
     سرد
    -0.06
     осіб
    -0.06
     flashy
    -0.06
     sexy
    -0.06
    POSITIVE LOGITS
    [jj
    0.07
    }.↵
    0.06
    tica
    0.06
    átní
    0.06
    ofile
    0.06
    Defines
    0.06
    (u
    0.06
     Multiply
    0.06
    _↵
    0.06
    Downloads
    0.06
    Act Density 0.000%

    No Known Activations