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

    Neuronpedia

    INDEX
    Explanations

    mention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merkez
    -0.07
    าตร
    -0.07
     спортив
    -0.07
    по
    -0.06
     varlık
    -0.06
     Raid
    -0.06
     lst
    -0.06
     miễn
    -0.06
    ılış
    -0.06
     hayvan
    -0.06
    POSITIVE LOGITS
     YORK
    0.07
    _utf
    0.07
    _only
    0.07
    King
    0.06
    Who
    0.06
     GO
    0.06
     Who
    0.06
    FORMAT
    0.06
    (image
    0.06
     agree
    0.06
    Act Density 0.014%

    No Known Activations