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

    Neuronpedia

    INDEX
    Explanations

    non-English words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apeutics
    0.41
    чке
    0.40
    дикатор
    0.40
    eritud
    0.39
    க்ச
    0.39
    舝
    0.39
    poque
    0.39
    欱
    0.39
    ᠮ
    0.39
     করির
    0.39
    POSITIVE LOGITS
     karena
    0.50
     व्याख्या
    0.44
     મળ
    0.43
     由于
    0.43
     እንዲሁ
    0.43
     因为
    0.43
    发现
    0.43
     Swansea
    0.42
    游
    0.42
     fluvial
    0.42
    Act Density 0.003%

    No Known Activations