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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <I
    -0.07
     bếp
    -0.06
     trolling
    -0.06
    .Utc
    -0.06
    ');?></
    -0.06
    orget
    -0.06
     AppleWebKit
    -0.06
    ager
    -0.06
    .Sm
    -0.06
    >\<^
    -0.06
    POSITIVE LOGITS
    Lbl
    0.07
    rive
    0.06
    матрива
    0.06
     fiscal
    0.06
     laisse
    0.06
    (cos
    0.06
    TextInput
    0.06
    childs
    0.06
     詳細
    0.06
    (shell
    0.06
    Act Density 0.018%

    No Known Activations