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

    Neuronpedia

    INDEX
    Explanations

    allergies and medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.12
    the
    1.06
    ing
    0.99
    ان
    0.98
    ும்
    0.92
    يج
    0.88
    ۔
    0.87
    Α
    0.86
    ில்
    0.82
    ة
    0.81
    POSITIVE LOGITS
    ↵↵
    1.10
     to
    0.92
    -
    0.92
    ↵
    0.89
     C
    0.85
     B
    0.85
    ys
    0.84
    8
    0.82
     P
    0.80
    ien
    0.80
    Act Density 0.002%

    No Known Activations