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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gz
    -0.07
    Bean
    -0.06
    Message
    -0.06
     uk
    -0.06
    (SQL
    -0.06
     dawn
    -0.06
     ω
    -0.06
     foreach
    -0.06
    (job
    -0.06
     senator
    -0.06
    POSITIVE LOGITS
    -clean
    0.07
     parts
    0.06
    ายใน
    0.06
     chứ
    0.06
    ().'/
    0.06
     cigaret
    0.06
     Stem
    0.06
    ATOM
    0.06
     posicion
    0.06
    ์,
    0.05
    Act Density 0.059%

    No Known Activations