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

    Neuronpedia

    INDEX
    Explanations

    Attaching objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STACK
    -0.07
     hides
    -0.07
    director
    -0.07
     Aston
    -0.07
    UPLE
    -0.07
     traumatic
    -0.07
     bul
    -0.07
    DD
    -0.06
    "];
    -0.06
    _algo
    -0.06
    POSITIVE LOGITS
    ансов
    0.05
     случа
    0.05
    Constants
    0.05
    cesso
    0.05
     Borg
    0.05
     наблю
    0.05
    ’app
    0.05
    ='{$
    0.05
     ゝ
    0.05
     ',
    0.05
    Act Density 0.097%

    No Known Activations