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

    Neuronpedia

    INDEX
    Explanations

    state of being

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

    separating clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ur
    0.82
     যা
    0.66
     Meille
    0.65
    3
    0.64
     สำหรับ
    0.63
     இதையடுத்து
    0.63
    aching
    0.63
     ৩
    0.62
     আমাদের
    0.61
     Für
    0.61
    POSITIVE LOGITS
    s
    1.25
    ی
    1.23
    t
    0.95
    х
    0.85
    sion
    0.71
    ség
    0.68
    я
    0.68
    the
    0.67
    ात
    0.64
    ק
    0.64
    Act Density 0.000%

    No Known Activations