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

    Neuronpedia

    INDEX
    Explanations

    NEGLIGENCE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pace
    -0.07
    vac
    -0.06
    or
    -0.06
    itle
    -0.06
     tablets
    -0.06
    нав
    -0.06
    record
    -0.06
     Tablets
    -0.06
    bios
    -0.06
    iou
    -0.06
    POSITIVE LOGITS
     моч
    0.07
    descending
    0.06
     못
    0.06
    59
    0.06
     reckless
    0.06
     Test
    0.06
     گرد
    0.06
    巡
    0.06
     něco
    0.06
    filtered
    0.06
    Act Density 0.000%

    No Known Activations