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

    Neuronpedia

    INDEX
    Explanations

    USD currency pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.77
    。
    0.77
     pressur
    0.74
     (
    0.74
     steril
    0.67
     cooker
    0.67
     (!)
    0.67
     सम्मेलन
    0.65
     vaporizer
    0.64
    0.64
    POSITIVE LOGITS
    ↵
    1.22
    at
    0.98
    ت
    0.98
    the
    0.95
    ل
    0.95
    و
    0.95
    and
    0.93
    т
    0.89
    ik
    0.88
     the
    0.85
    Act Density 0.000%

    No Known Activations