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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fr
    -0.07
    Cd
    -0.07
     prostitu
    -0.06
     rast
    -0.06
     lp
    -0.06
    .localized
    -0.06
    _aa
    -0.06
     owl
    -0.06
    (".");↵
    -0.06
     пути
    -0.06
    POSITIVE LOGITS
     Seamless
    0.07
     introduce
    0.07
    >L
    0.07
     BIOS
    0.07
    .Σ
    0.06
     bağ
    0.06
    Form
    0.06
     Prices
    0.06
    ----------↵↵
    0.06
    103
    0.06
    Act Density 0.054%

    No Known Activations