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

    Neuronpedia

    INDEX
    Explanations

    code and forum snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otation
    -0.07
    constructor
    -0.06
    ["$
    -0.06
     damping
    -0.06
    bread
    -0.06
    bung
    -0.06
     pendant
    -0.06
     gm
    -0.06
     defendant
    -0.06
    。あ
    -0.06
    POSITIVE LOGITS
     воспал
    0.07
    erek
    0.07
    αλλ
    0.07
    _lex
    0.06
     telah
    0.06
     вас
    0.06
     хотел
    0.06
    Vals
    0.06
     wParam
    0.06
    ели
    0.06
    Act Density 0.000%

    No Known Activations