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

    Neuronpedia

    INDEX
    Explanations

    bach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ervention
    -0.07
    vel
    -0.07
    .dev
    -0.07
     minority
    -0.07
    eten
    -0.06
     treasure
    -0.06
    /routes
    -0.06
    <Test
    -0.06
     freeway
    -0.06
     stellen
    -0.06
    POSITIVE LOGITS
    _gui
    0.07
     daughter
    0.07
     coverage
    0.07
    怀疑
    0.07
    ipline
    0.06
    了一会
    0.06
    了一
    0.06
     widać
    0.06
    🅅
    0.06
     Можно
    0.06
    Act Density 0.000%

    No Known Activations