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

    Neuronpedia

    INDEX
    Explanations

    cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .EventSystems
    -0.07
     ethos
    -0.07
     herd
    -0.07
    lect
    -0.07
    .plan
    -0.06
     Twenty
    -0.06
    턴
    -0.06
    endment
    -0.06
     Trends
    -0.06
    avenport
    -0.06
    POSITIVE LOGITS
    üslü
    0.06
    Marsh
    0.06
    _BLOCKS
    0.06
    SCRIPTOR
    0.06
    _MM
    0.06
    _ROUND
    0.06
     Bakan
    0.06
     граду
    0.06
    _merged
    0.06
     dishwasher
    0.06
    Act Density 0.019%

    No Known Activations