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

    Neuronpedia

    INDEX
    Explanations

    Acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.66
    ate
    0.60
    al
    0.59
     z
    0.58
     U
    0.55
     Z
    0.55
    atet
    0.52
     Island
    0.52
    ro
    0.51
    alit
    0.51
    POSITIVE LOGITS
    Acts
    0.64
    ਮ
    0.59
    ਾਨੂੰ
    0.56
    َم
    0.55
     Acts
    0.54
    จาก
    0.51
    PROFILE
    0.50
    種の
    0.50
    ﻒ
    0.49
    ORDIN
    0.49
    Act Density 0.002%

    No Known Activations