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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and scenarios involving "if."

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

    "if" followed by a pronoun or adverb

    np_acts-logits-general · gemini-2.0-flash

    if properly or appropriately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quæ
    -0.59
    esModule
    -0.56
    CloseOperation
    -0.55
     مؤرشف
    -0.55
     uuidv
    -0.53
    Mandatory
    -0.51
    клопе
    -0.51
    ########.
    -0.51
    DllImport
    -0.51
    出版年
    -0.50
    POSITIVE LOGITS
     properly
    1.08
    properly
    0.96
     Properly
    0.94
     appropriately
    0.94
     proper
    0.84
     correctly
    0.81
    Proper
    0.78
    proper
    0.78
     PROPER
    0.75
     suitably
    0.74
    Act Density 0.255%

    No Known Activations