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

    Neuronpedia

    INDEX
    Explanations

    initials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coz
    -0.06
     kans
    -0.06
     пацієн
    -0.06
    cü
    -0.06
    EditText
    -0.06
     Cant
    -0.06
    クラ
    -0.06
     tranh
    -0.06
     cans
    -0.06
     Owners
    -0.06
    POSITIVE LOGITS
    /{$
    0.07
    ounty
    0.07
    _;↵
    0.07
    _parms
    0.07
    ][(
    0.06
    説明
    0.06
    <cv
    0.06
    ála
    0.06
    قى
    0.06
    ,V
    0.06
    Act Density 0.067%

    No Known Activations