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

    Neuronpedia

    INDEX
    Explanations

    online

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    禳
    0.55
     కూడా
    0.49
    泬
    0.46
    ല്ലാതെ
    0.45
    沧
    0.45
    尣
    0.45
    اري
    0.45
    zeptember
    0.45
    ีก
    0.44
     نیز
    0.44
    POSITIVE LOGITS
     millions
    0.44
     dull
    0.40
    int
    0.38
     opportunities
    0.37
    0.37
     y
    0.36
     Millions
    0.36
     e
    0.36
    great
    0.36
     frequencies
    0.35
    Act Density 0.018%

    No Known Activations