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

    Neuronpedia

    INDEX
    Explanations

    imperative and conditional phrases related to obligations or recommendations

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

    modal verbs followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.68
     Efq
    -0.66
    ValueStyle
    -0.66
     transfieras
    -0.63
    FunctionFlags
    -0.61
     MutableLiveData
    -0.61
     CURIAM
    -0.60
     varandra
    -0.60
     Audiodateien
    -0.60
     ModelExpression
    -0.60
    POSITIVE LOGITS
     jail
    0.34
    m
    0.34
     forego
    0.33
     Jordan
    0.33
    A
    0.33
    wapV
    0.32
    d
    0.32
     Go
    0.32
     A
    0.31
     додат
    0.31
    Act Density 0.054%

    No Known Activations