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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -but
    -0.07
     onslaught
    -0.07
    (LayoutInflater
    -0.06
     widths
    -0.06
    řad
    -0.06
    idential
    -0.06
    ’autres
    -0.06
     búsqueda
    -0.06
     advancing
    -0.06
     believer
    -0.06
    POSITIVE LOGITS
     neu
    0.07
    (team
    0.06
    .General
    0.06
    (foo
    0.06
    Startup
    0.06
    .backend
    0.06
    ยวข
    0.06
    Manufacturer
    0.06
    ैज
    0.06
     UIT
    0.06
    Act Density 0.000%

    No Known Activations