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

    Neuronpedia

    INDEX
    Explanations

    programming questions and text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .colors
    -0.07
     литер
    -0.07
     mapper
    -0.07
     appe
    -0.07
    (sequence
    -0.06
    поч
    -0.06
    olver
    -0.06
     euros
    -0.06
     imped
    -0.06
     בהת
    -0.06
    POSITIVE LOGITS
    一個人
    0.07
    很清楚
    0.07
    >$
    0.07
    Jan
    0.06
    [*
    0.06
    "↵↵
    0.06
    ”↵↵
    0.06
    𝒷
    0.06
     realizes
    0.06
    arn
    0.06
    Act Density 0.006%

    No Known Activations