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

    Neuronpedia

    INDEX
    Explanations

    three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    新作
    0.41
     kalau
    0.40
     ^=
    0.40
     keduanya
    0.39
     هوا
    0.38
    Linda
    0.38
     kebijakan
    0.38
    มากขึ้น
    0.38
     friendship
    0.37
     সময়
    0.37
    POSITIVE LOGITS
     drei
    0.44
    three
    0.43
    interpret
    0.43
     Vocabulary
    0.42
     three
    0.42
    Vocabulary
    0.42
    interpr
    0.41
    0.41
     stimulates
    0.41
     तीन
    0.40
    Act Density 0.002%

    No Known Activations