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

    Neuronpedia

    INDEX
    Explanations

    DIY ethos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ipotesi
    0.40
     є
    0.39
    ört
    0.38
     технология
    0.38
     자동
    0.36
     culprits
    0.35
     они
    0.35
     업체
    0.35
     방식
    0.34
     hypersurface
    0.34
    POSITIVE LOGITS
     நியூ
    0.48
    Packing
    0.45
    Fran
    0.45
     FRAN
    0.43
    ियारों
    0.42
    Gmail
    0.42
    Cruz
    0.41
    codegen
    0.40
    CROSS
    0.39
    聃
    0.39
    Act Density 0.001%

    No Known Activations