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

    Neuronpedia

    INDEX
    Explanations

    poetry and literature

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     departure
    -0.08
    idence
    -0.07
    ויות
    -0.07
     חד
    -0.07
    .tiles
    -0.07
    重新
    -0.07
    차
    -0.07
    _UPPER
    -0.07
     ngược
    -0.07
    <Data
    -0.07
    POSITIVE LOGITS
     workout
    0.07
     FEMA
    0.07
    ℟
    0.07
     fame
    0.06
    genome
    0.06
     Grad
    0.06
    gov
    0.06
     Synopsis
    0.06
     RL
    0.06
     fried
    0.06
    Act Density 0.182%

    No Known Activations