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

    Neuronpedia

    INDEX
    Explanations

    of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disreg
    0.84
    总是
    0.82
     exacerbate
    0.82
     shortfall
    0.80
     всегда
    0.80
     neglects
    0.80
     fails
    0.79
    常に
    0.79
     특정
    0.78
    fails
    0.78
    POSITIVE LOGITS
     finally
    2.34
     finalmente
    2.01
    finally
    1.98
     endlich
    1.91
    Finally
    1.90
     Finally
    1.89
    终于
    1.83
    終於
    1.79
    ようやく
    1.77
     наконец
    1.76
    Act Density 0.119%

    No Known Activations