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

    Neuronpedia

    INDEX
    Explanations

    references to a specific target or item within a document

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

    target and descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MOM
    -0.34
     verv
    -0.34
     Perrin
    -0.34
     rowCount
    -0.34
    Collections
    -0.33
    OrWhiteSpace
    -0.33
    
    -0.33
    createTable
    -0.32
     He
    -0.31
     Perr
    -0.31
    POSITIVE LOGITS
     target
    1.69
     Target
    1.60
    Target
    1.48
     TARGET
    1.48
    target
    1.47
     cible
    1.46
     targets
    1.40
     Targets
    1.36
    TARGET
    1.34
    getTarget
    1.25
    Act Density 0.025%

    No Known Activations