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

    Neuronpedia

    INDEX
    Explanations

    based on, to tell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     лигасы
    0.50
    íř
    0.46
    ب
    0.46
    uş
    0.45
    iação
    0.44
    वता
    0.44
     morphed
    0.44
    諷
    0.43
    勰
    0.43
     currencies
    0.41
    POSITIVE LOGITS
    戝
    0.52
    fork
    0.45
    Spatial
    0.44
     Ministerio
    0.44
    ൃശ
    0.43
    Grace
    0.43
     parche
    0.42
    raphics
    0.42
    ալ
    0.42
    гра
    0.42
    Act Density 0.012%

    No Known Activations