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

    Neuronpedia

    INDEX
    Explanations

    code blocks and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     misfort
    0.43
     turno
    0.41
    伨
    0.40
     đoạn
    0.39
    玽
    0.39
    पीड़न
    0.39
    ्राष्ट
    0.39
     совокуп
    0.38
     keto
    0.38
    াকাছি
    0.38
    POSITIVE LOGITS
    ا
    0.52
    i
    0.45
    U
    0.43
    u
    0.43
    dA
    0.43
     Conversion
    0.42
     Responsive
    0.42
    ਾ
    0.41
    —
    0.40
     Recovery
    0.40
    Act Density 0.000%

    No Known Activations