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

    Neuronpedia

    INDEX
    Explanations

    generating model code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    струк
    0.66
    主
    0.63
    izophren
    0.63
    BDF
    0.61
    ildet
    0.59
    Research
    0.59
    幂
    0.58
    eliti
    0.58
     ezzel
    0.57
     шли
    0.57
    POSITIVE LOGITS
     talál
    0.85
     Termin
    0.80
     Highlight
    0.76
     Auburn
    0.75
     Canoe
    0.74
     Term
    0.74
     entdecken
    0.74
     termos
    0.74
    ल्फी
    0.73
     Thermal
    0.73
    Act Density 0.076%

    No Known Activations