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

    Neuronpedia

    INDEX
    Explanations

    opinionated evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၌
    0.68
    하였다
    0.64
     seldom
    0.61
    하였
    0.60
     चिकित्सकों
    0.55
     किंतु
    0.54
    persons
    0.54
     अवश्य
    0.53
     اکنون
    0.53
    하여
    0.52
    POSITIVE LOGITS
     dudes
    1.26
     badass
    1.21
     shitty
    1.20
     dude
    1.18
     crappy
    1.14
     gotta
    1.06
    めっちゃ
    1.02
     pretty
    1.02
     kinda
    1.02
     freaking
    1.01
    Act Density 0.007%

    No Known Activations