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

    Neuronpedia

    INDEX
    Explanations

    verbs often associated with actions taken by people, especially in positions of power.

    oai_token-act-pair · gemini-2.0-flash

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.67
    PhysRevD
    -0.65
    Plus
    -0.61
     Resonance
    -0.59
     secondly
    -0.59
     Plus
    -0.57
    andinavia
    -0.57
     cioc
    -0.57
    AddTagHelper
    -0.56
    pleen
    -0.55
    POSITIVE LOGITS
    setDo
    0.47
     ba
    0.44
    aarrggbb
    0.43
     NSCoder
    0.42
    aufen
    0.40
    protos
    0.40
    urm
    0.38
    SpringBootTest
    0.36
     iprot
    0.36
    ásban
    0.36
    Act Density 19.222%

    No Known Activations