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

    Neuronpedia

    INDEX
    Explanations

    to have value or use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /
    0.86
    0.85
     all
    0.75
    /
    0.75
     ​​
    0.74
     six
    0.73
    )
    0.72
     is
    0.69
     get
    0.68
     by
    0.67
    POSITIVE LOGITS
    想象
    1.23
     evidentemente
    1.23
     adecuadas
    1.21
     ಅಂಶ
    1.21
     investimentos
    1.21
     efectiva
    1.19
     coseno
    1.16
     efectivamente
    1.15
    effetto
    1.15
     بسيطه
    1.14
    Act Density 0.030%

    No Known Activations