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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     možnosti
    0.82
    බැ
    0.82
    酺
    0.82
    ровку
    0.80
     نقصان
    0.79
     userService
    0.78
     недоста
    0.78
    届け
    0.78
     dzie
    0.77
    賂
    0.74
    POSITIVE LOGITS
     rectangular
    1.88
     cylindrical
    1.81
     grayish
    1.75
    rectangular
    1.68
     whitish
    1.67
     brownish
    1.65
     reddish
    1.63
     yellowish
    1.61
     sleek
    1.58
     slender
    1.58
    Act Density 0.694%

    No Known Activations