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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     growth
    -0.07
    _RA
    -0.07
     work
    -0.07
     meat
    -0.07
    ुड
    -0.06
     Work
    -0.06
     Em
    -0.06
     Bern
    -0.06
     WORK
    -0.06
    елен
    -0.06
    POSITIVE LOGITS
     ascertain
    0.07
    _attrib
    0.07
    .toArray
    0.07
    etical
    0.07
    ่าจะ
    0.07
     οπο
    0.07
     पत
    0.07
    наслід
    0.07
    ате
    0.06
    *((
    0.06
    Act Density 0.008%

    No Known Activations