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

    Neuronpedia

    INDEX
    Explanations

    detail prompt accuracy folder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்திலும்
    0.47
     مربوط
    0.42
    andos
    0.41
     छोड़कर
    0.40
    த்திற்கும்
    0.40
    ത്തിലും
    0.38
     lié
    0.37
    මත්
    0.37
     visant
    0.37
     ማለት
    0.36
    POSITIVE LOGITS
    នូវ
    1.34
     what
    0.96
     how
    0.80
     את
    0.78
     those
    0.74
    什么是
    0.69
     آنچه
    0.69
    what
    0.64
     why
    0.61
     hvad
    0.59
    Act Density 0.027%

    No Known Activations