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

    Neuronpedia

    INDEX
    Explanations

    Code/documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Τα
    -0.06
     사이트
    -0.06
     patches
    -0.06
    _aw
    -0.06
    管理员
    -0.06
    $tpl
    -0.06
     isset
    -0.06
    .matmul
    -0.06
     deploy
    -0.06
     broth
    -0.06
    POSITIVE LOGITS
     EAST
    0.09
     Fountain
    0.06
     éc
    0.06
    (parameter
    0.06
    {Name
    0.06
     refusal
    0.06
    )==
    0.06
     disreg
    0.06
    0.06
    *(-
    0.06
    Act Density 0.022%

    No Known Activations