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

    Neuronpedia

    INDEX
    Explanations

    free or at no cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     effector
    0.45
     zoomed
    0.44
     smoothness
    0.43
     questioned
    0.42
     uttered
    0.41
     গ্রন্থে
    0.41
    cribed
    0.40
     proximal
    0.40
     distancing
    0.40
    考える
    0.40
    POSITIVE LOGITS
    免费
    1.34
    免費
    1.30
     бесплат
    1.30
     무료
    1.27
    無料
    1.21
     free
    1.20
     ücretsiz
    1.20
     gratis
    1.19
    free
    1.15
    無料で
    1.15
    Act Density 0.219%

    No Known Activations