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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions or the importance of decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    to and importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.43
    principalTable
    -0.38
    TagMode
    -0.38
    -0.36
    ⇓
    -0.36
    ☕
    -0.35
    nemies
    -0.35
    astéroïdes
    -0.35
    Extr
    -0.34
    Климат
    -0.34
    POSITIVE LOGITS
     NavController
    0.60
    WebElementEntity
    0.47
    twimg
    0.47
    TestingModule
    0.45
    RTLI
    0.44
    Portale
    0.43
    webElement
    0.42
     EconPapers
    0.42
    modelBuilder
    0.42
    RTCF
    0.42
    Act Density 0.143%

    No Known Activations