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

    Neuronpedia

    INDEX
    Explanations

    likelihood estimator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IsNot
    -0.07
     Quiz
    -0.07
    Forgot
    -0.07
     negro
    -0.06
    <>();↵
    -0.06
     transf
    -0.06
    Sans
    -0.06
    <Character
    -0.06
     relational
    -0.06
     allocator
    -0.06
    POSITIVE LOGITS
    εκ
    0.07
    chartInstance
    0.06
    各种
    0.06
     сохран
    0.06
    로나
    0.06
    bild
    0.06
     puan
    0.06
    .colorbar
    0.06
    розум
    0.06
    /AIDS
    0.06
    Act Density 0.012%

    No Known Activations