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

    Neuronpedia

    INDEX
    Explanations

    Ancient structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اش
    0.71
    از
    0.60
    اگر
    0.57
    agamanam
    0.57
    ج
    0.56
    ILLE
    0.55
    కాం
    0.55
    ຽ
    0.54
    ش
    0.54
    يطان
    0.54
    POSITIVE LOGITS
    en
    0.61
    fection
    0.53
     folder
    0.49
     Myers
    0.48
     Low
    0.47
     आम
    0.46
    woord
    0.46
     low
    0.46
    icketts
    0.46
     et
    0.46
    Act Density 0.000%

    No Known Activations