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

    Neuronpedia

    INDEX
    Explanations

    measurements and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tongues
    -0.07
    findOne
    -0.07
    humidity
    -0.06
     retirement
    -0.06
    .nextSibling
    -0.06
     zipper
    -0.06
    eligible
    -0.06
    _sp
    -0.06
     visibility
    -0.06
    So
    -0.06
    POSITIVE LOGITS
    .swagger
    0.06
     frase
    0.06
    故
    0.06
    asic
    0.06
    duto
    0.06
     enfermed
    0.06
     Vintage
    0.06
     Nan
    0.06
     tasked
    0.06
     Под
    0.06
    Act Density 0.002%

    No Known Activations