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

    Neuronpedia

    INDEX
    Explanations

    assume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sets
    -0.07
    ITES
    -0.07
     Filtering
    -0.07
    étique
    -0.07
    ạp
    -0.07
     filtering
    -0.06
    zens
    -0.06
     hiding
    -0.06
     스트
    -0.06
     Films
    -0.06
    POSITIVE LOGITS
     assume
    0.08
    onda
    0.06
    gpio
    0.06
     CCT
    0.06
     james
    0.06
    ござ
    0.06
     GIT
    0.06
    });↵↵↵↵
    0.06
    !,
    0.06
     cout
    0.06
    Act Density 0.016%

    No Known Activations