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

    Neuronpedia

    INDEX
    Explanations

    references to scenic views or locations that offer an overview

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

    overlooks facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.62
     FetchType
    -0.58
    ftagPool
    -0.56
     pleaſure
    -0.56
    UserScript
    -0.51
     auroit
    -0.51
     BIBSYS
    -0.50
     faſt
    -0.50
    AnimationsModule
    -0.49
    stateProvider
    -0.49
    POSITIVE LOGITS
     overlooking
    1.73
     overlooks
    1.41
     overlook
    1.23
     overlooked
    0.82
     overseeing
    0.80
    over
    0.74
    瞰
    0.70
     over
    0.69
     Overse
    0.68
     Over
    0.66
    Act Density 0.002%

    No Known Activations