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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their implications in legal or formal contexts

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

    Preceding a modal verb (can, could, might, may)

    np_acts-logits-general · gemini-2.0-flash

    modal verbs with qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.71
    StructEnd
    -0.64
     nahilalakip
    -0.63
     linkovi
    -0.62
    цездатний
    -0.61
     lenker
    -0.61
    MockMvc
    -0.60
     Bescheid
    -0.58
    RetentionPolicy
    -0.57
    InvalidProtocol
    -0.57
    POSITIVE LOGITS
     well
    0.77
     itself
    0.73
     properly
    0.69
     safely
    0.64
     in
    0.63
     parha
    0.63
    ,
    0.62
     rightly
    0.62
     hardly
    0.61
     at
    0.61
    Act Density 0.455%

    No Known Activations