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

    Neuronpedia

    INDEX
    Explanations

    period followed by "It"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     или
    0.98
    (
    0.91
     particularmente
    0.89
     demikian
    0.87
     vagy
    0.86
    (/
    0.86
    いたり
    0.85
     accordingly
    0.85
     or
    0.84
     atau
    0.83
    POSITIVE LOGITS
     Allow
    0.74
     She
    0.73
    iosi
    0.72
     allow
    0.69
     Allows
    0.69
     He
    0.68
    vere
    0.67
     Resolve
    0.66
    ঙে
    0.66
     あなた
    0.65
    Act Density 0.477%

    No Known Activations