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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Client
    -0.08
    WithTitle
    -0.07
    Selective
    -0.07
    ril
    -0.07
    thanks
    -0.06
    (dllexport
    -0.06
    Thursday
    -0.06
     hardcore
    -0.06
    Queries
    -0.06
     напит
    -0.06
    POSITIVE LOGITS
    datas
    0.06
    .vs
    0.06
    —I
    0.06
    板
    0.06
     Re
    0.06
    LIGHT
    0.06
     lyn
    0.06
    .RES
    0.05
    ?>>↵
    0.05
    ["$
    0.05
    Act Density 0.124%

    No Known Activations