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

    Neuronpedia

    INDEX
    Explanations

    break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forth
    0.80
     march
    0.74
    forth
    0.74
     lauf
    0.73
    iral
    0.69
     astray
    0.68
    न्यास
    0.68
    -
    0.66
     flor
    0.65
     einzelnen
    0.65
    POSITIVE LOGITS
     ቢ
    0.87
    엘
    0.75
    టే
    0.73
    없
    0.72
    اا
    0.72
     సౌ
    0.72
    看着
    0.70
    譁
    0.70
    रिया
    0.70
    难度
    0.69
    Act Density 0.022%

    No Known Activations