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

    Neuronpedia

    INDEX
    Explanations

    app: identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     State
    0.50
    State
    0.48
    STATE
    0.43
     სახელმწიფო
    0.43
    state
    0.39
    [
    0.38
    yj
    0.37
     Surrogate
    0.37
    ytic
    0.37
    yin
    0.36
    POSITIVE LOGITS
    тить
    0.43
    тория
    0.42
    чном
    0.41
    言
    0.39
     odpow
    0.38
    ար
    0.37
    ક્ષા
    0.36
    করিয়
    0.36
    пас
    0.35
     podríamos
    0.35
    Act Density 0.002%

    No Known Activations