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

    Neuronpedia

    INDEX
    Explanations

    age in years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.92
    ك
    0.89
    i
    0.88
    י
    0.86
    ла
    0.81
    ള
    0.75
    یت
    0.75
    カ
    0.75
    ת
    0.73
    idencia
    0.72
    POSITIVE LOGITS
     in
    0.85
    nel
    0.65
    㚼
    0.61
    layered
    0.59
    I
    0.59
     medis
    0.58
    لى
    0.57
    semble
    0.57
    nement
    0.55
     annih
    0.55
    Act Density 0.012%

    No Known Activations