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

    Neuronpedia

    INDEX
    Explanations

    risk within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     good
    0.41
    សូម
    0.37
     hãy
    0.36
     कृपया
    0.36
    需要
    0.36
     alongside
    0.35
     embarked
    0.35
    画
    0.35
    请
    0.35
     हाम
    0.35
    POSITIVE LOGITS
    Called
    0.40
     metastasis
    0.39
     metastatic
    0.37
    Empleado
    0.37
     поток
    0.37
     metastable
    0.36
    utional
    0.36
     まで
    0.35
    Confusion
    0.35
    äm
    0.35
    Act Density 0.000%

    No Known Activations