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

    Neuronpedia

    INDEX
    Explanations

    willy-nilly, abandon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KUR
    -0.07
     Duchess
    -0.06
    杨
    -0.06
    ETH
    -0.06
     Mehmet
    -0.06
    _wheel
    -0.06
    StateManager
    -0.06
    338
    -0.06
    342
    -0.06
    Craig
    -0.06
    POSITIVE LOGITS
     horrend
    0.07
     Within
    0.06
    .DropDownList
    0.06
    .em
    0.06
     Three
    0.06
    ):↵
    0.06
    _possible
    0.06
     checker
    0.06
     Ini
    0.06
     Enter
    0.06
    Act Density 0.049%

    No Known Activations