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

    Neuronpedia

    INDEX
    Explanations

    vice versa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ні
    1.74
    ^{\#}\
    1.64
    人士
    1.60
    RAC
    1.55
    te
    1.51
     closest
    1.48
    r
    1.47
    क
    1.47
     cerevisiae
    1.47
    loaf
    1.46
    POSITIVE LOGITS
     hardwoods
    1.57
    ни
    1.56
    檛
    1.54
     analogies
    1.52
     annealing
    1.52
     Ovaj
    1.51
     ordinances
    1.50
    𝖐
    1.50
     mineralization
    1.48
     века
    1.44
    Act Density 0.014%

    No Known Activations