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

    Neuronpedia

    INDEX
    Explanations

    degree SpaceX, Think SpaceX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    预防
    0.49
    screen
    0.49
    áže
    0.47
    test
    0.47
     markedly
    0.46
     preventive
    0.46
    LL
    0.46
    UT
    0.45
    target
    0.45
    hiver
    0.45
    POSITIVE LOGITS
     acus
    0.49
     artillery
    0.49
     articol
    0.48
     atmosfera
    0.48
    م
    0.46
     sectores
    0.46
     ferries
    0.44
     volonté
    0.44
     automobiles
    0.44
     ideia
    0.43
    Act Density 0.004%

    No Known Activations