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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rahman
    -0.07
     stakes
    -0.06
    .descripcion
    -0.06
    童
    -0.06
    .Xtra
    -0.06
     demons
    -0.06
    ?>↵
    -0.06
    anneer
    -0.06
     hodin
    -0.05
    로운
    -0.05
    POSITIVE LOGITS
     слаб
    0.07
    Waiting
    0.07
    ถม
    0.07
    чить
    0.07
    AWN
    0.07
    อห
    0.06
    เห
    0.06
    abus
    0.06
     ABOVE
    0.06
     BY
    0.06
    Act Density 0.131%

    No Known Activations