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

    Neuronpedia

    INDEX
    Explanations

    code and math syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档
    0.83
    <unused1110>
    0.80
    ystick
    0.79
     crept
    0.79
    ევე
    0.78
     normalmente
    0.78
     correctAnswer
    0.77
    Tarea
    0.74
    ifert
    0.74
    唥
    0.74
    POSITIVE LOGITS
     Read
    0.69
    ാരി
    0.69
     familiar
    0.68
    стран
    0.65
     doubt
    0.65
     Ind
    0.61
    ރު
    0.61
    Offering
    0.61
    読
    0.60
    ovie
    0.60
    Act Density 0.019%

    No Known Activations