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

    Neuronpedia

    INDEX
    Explanations

    i'll followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite

    I'll cover or organize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.98
     a
    0.94
     I
    0.94
    т
    0.82
    u
    0.80
     has
    0.79
    .
    0.79
    ↵
    0.78
    s
    0.78
    t
    0.77
    POSITIVE LOGITS
    不過
    0.82
    不过
    0.77
    ك
    0.76
    م
    0.75
    지만
    0.74
    在
    0.73
    știg
    0.72
    ত্যাশিত
    0.71
    O
    0.70
    С
    0.70
    Act Density 0.155%

    No Known Activations