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

    Neuronpedia

    INDEX
    Explanations

    prefix `a` or `da`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ያዎች
    0.38
    EI
    0.38
    J
    0.36
     जंग
    0.36
    Chancellor
    0.36
    Ever
    0.36
     Quelques
    0.36
    ﺠ
    0.35
    فيذ
    0.35
     déterminer
    0.34
    POSITIVE LOGITS
     particules
    0.38
    iffen
    0.38
    🎃
    0.37
     excess
    0.37
    吧
    0.37
    atsiya
    0.36
     bắt
    0.36
    imak
    0.36
    ⽤
    0.36
    した
    0.35
    Act Density 0.032%

    No Known Activations