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

    Neuronpedia

    INDEX
    Explanations

    Programming code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    郯
    -0.07
    grese
    -0.07
    _-_
    -0.07
    _iter
    -0.07
    莘
    -0.07
    flater
    -0.06
    .Canvas
    -0.06
    (blob
    -0.06
    .refresh
    -0.06
    uis
    -0.06
    POSITIVE LOGITS
    Permanent
    0.07
    جسد
    0.07
     rotating
    0.06
     retrospect
    0.06
    projectId
    0.06
     principle
    0.06
     Korea
    0.06
     herd
    0.06
     shame
    0.06
     spiritually
    0.06
    Act Density 0.015%

    No Known Activations