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

    Neuronpedia

    INDEX
    Explanations

    value =, dressing modestly, data comes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awks
    0.47
    ování
    0.47
    学习
    0.45
    ierung
    0.45
    urbation
    0.45
    люби
    0.44
    chievement
    0.44
    ្ត
    0.43
    räume
    0.43
    ップ
    0.43
    POSITIVE LOGITS
    r
    0.50
    Ladies
    0.46
     የሆነ
    0.45
     EMBO
    0.43
    t
    0.43
    ILL
    0.43
     mixes
    0.43
    MS
    0.43
    MU
    0.42
    Mus
    0.42
    Act Density 0.000%

    No Known Activations