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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ETCH
    -0.07
    oders
    -0.07
    laps
    -0.07
    コード
    -0.07
    LOOR
    -0.07
     bitch
    -0.07
    etical
    -0.06
     affiliation
    -0.06
    ênh
    -0.06
    .has
    -0.06
    POSITIVE LOGITS
    …and
    0.06
     overshadow
    0.06
     }}">
    0.06
     StringSplitOptions
    0.06
    ственная
    0.06
     subconscious
    0.06
    alim
    0.06
    FFFFFFFF
    0.06
     حوزه
    0.06
    (hwnd
    0.06
    Act Density 0.836%

    No Known Activations