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

    Neuronpedia

    INDEX
    Explanations

    patterns related to response handling in code

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

    Code or queries with assignment operators (=) or dollar signs ($)

    np_acts-logits-general · gemini-2.0-flash

    in query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.63
    ValueStyle
    -0.59
    HasForeignKey
    -0.54
     tartalomajánló
    -0.54
    IVEREF
    -0.53
    ьаж
    -0.51
    Portale
    -0.50
    Portail
    -0.50
     kaarangay
    -0.50
     NSCoder
    -0.48
    POSITIVE LOGITS
     VIDEOTAPE
    0.33
    RunWith
    0.32
    oughed
    0.32
     hydro
    0.31
     doInBackground
    0.31
     quickly
    0.31
     operação
    0.30
     surpresa
    0.29
     quickest
    0.29
     attempted
    0.29
    Act Density 0.301%

    No Known Activations