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

    Neuronpedia

    INDEX
    Explanations

    Software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     growers
    -0.07
     Bethlehem
    -0.07
     observer
    -0.07
     projects
    -0.06
    pees
    -0.06
     plata
    -0.06
    .MESSAGE
    -0.06
     sound
    -0.06
     seized
    -0.06
    _planes
    -0.06
    POSITIVE LOGITS
    こちら
    0.07
    /gui
    0.06
    obbled
    0.06
     같이
    0.06
    ()."
    0.06
     зак
    0.06
     Latvia
    0.06
    __[
    0.06
    addtogroup
    0.06
     Однак
    0.06
    Act Density 0.310%

    No Known Activations