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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lip
    -0.06
    ucose
    -0.06
    athlon
    -0.06
    _income
    -0.06
     Cuisine
    -0.05
     pit
    -0.05
    <O
    -0.05
     supports
    -0.05
     robust
    -0.05
     stomach
    -0.05
    POSITIVE LOGITS
     messagebox
    0.07
    .lists
    0.07
    .Scan
    0.07
     gü
    0.06
    .fetchone
    0.06
    ету
    0.06
     возв
    0.06
     انقل
    0.06
     vypad
    0.06
     이번
    0.06
    Act Density 0.035%

    No Known Activations