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

    Neuronpedia

    INDEX
    Explanations

    trim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ones
    -0.07
    냥
    -0.07
    혼
    -0.06
    “If
    -0.06
    PRS
    -0.06
    lek
    -0.06
    agation
    -0.06
    chodu
    -0.06
    imb
    -0.06
     Expo
    -0.06
    POSITIVE LOGITS
     sanitize
    0.07
    .Ed
    0.07
    etheus
    0.06
    .UPDATE
    0.06
     Ansi
    0.06
     stabbed
    0.06
    ↵    ↵↵
    0.06
    .Drawing
    0.06
     pupper
    0.06
    .getElementById
    0.06
    Act Density 0.112%

    No Known Activations