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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     partir
    -0.06
     Harlem
    -0.06
    _assignment
    -0.06
     Double
    -0.06
    Queen
    -0.06
    _todo
    -0.06
     sonst
    -0.06
     trò
    -0.06
    泳
    -0.06
    POSITIVE LOGITS
    (groups
    0.06
    Tutorial
    0.06
     Bian
    0.06
    .DropDownStyle
    0.06
    ظف
    0.06
    Nib
    0.06
    辺
    0.06
    리스
    0.06
    TOR
    0.06
    [msg
    0.06
    Act Density 0.053%

    No Known Activations