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

    Neuronpedia

    INDEX
    Explanations

    animal, only, shoe, done, attribute, children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []*
    0.83
     tzv
    0.81
     {@
    0.79
     unrestricted
    0.77
     /*
    0.76
     tzw
    0.75
     constructor
    0.74
    qttr
    0.73
     {}".
    0.71
    𝘮
    0.71
    POSITIVE LOGITS
    .''
    0.76
    энне
    0.73
    走出
    0.72
     مرکزی
    0.72
    ल्याण
    0.71
    ^^
    0.69
     γεγον
    0.69
    ขึ้น
    0.67
     და
    0.67
    slaught
    0.66
    Act Density 0.147%

    No Known Activations