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

    Neuronpedia

    INDEX
    Explanations

    vacuum, cryogenic, gases, pneumatic, magnetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adhipp
    0.60
     кандай
    0.58
     жөнүндө
    0.57
    bindingFields
    0.57
    唥
    0.57
     înviat
    0.56
    㵄
    0.56
     sociali
    0.55
    㿝
    0.55
     vuccanti
    0.54
    POSITIVE LOGITS
    com
    0.69
    K
    0.66
     high
    0.65
    製
    0.63
     up
    0.62
    W
    0.62
     gas
    0.61
    T
    0.61
    co
    0.61
     air
    0.60
    Act Density 0.107%

    No Known Activations