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

    Neuronpedia

    INDEX
    Explanations

    code tokens after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    药物
    0.42
    嗽
    0.41
    quefois
    0.40
    VSLU
    0.40
     सुष
    0.40
    chyné
    0.39
    鱻
    0.39
    opathie
    0.38
    琬
    0.38
    鼈
    0.38
    POSITIVE LOGITS
    s
    0.51
     was
    0.49
     were
    0.38
     }
    0.38
     داشت
    0.35
    get
    0.35
     _
    0.35
     has
    0.34
     |
    0.34
     cas
    0.34
    Act Density 0.012%

    No Known Activations