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

    Neuronpedia

    INDEX
    Explanations

    obtain easily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     בס
    0.63
    են
    0.62
     จับ
    0.59
     שני
    0.59
     inadequate
    0.57
     beinhaltet
    0.56
     않는다
    0.56
    ceptible
    0.56
    처리
    0.55
    정
    0.55
    POSITIVE LOGITS
     easily
    1.52
     obtain
    1.28
     enjoy
    1.27
     customize
    1.25
     see
    1.21
    easily
    1.20
     get
    1.19
     receive
    1.19
     facilement
    1.19
     learn
    1.17
    Act Density 0.774%

    No Known Activations