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

    Neuronpedia

    INDEX
    Explanations

    elements and parameters related to technical programming details

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

    code snippets and programming language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.43
    WithMany
    -0.32
    höhung
    -0.32
    ettbewerb
    -0.31
     canela
    -0.31
     Rico
    -0.31
     death
    -0.29
    </
    -0.29
     pajero
    -0.29
     typelib
    -0.28
    POSITIVE LOGITS
    kate
    0.80
    fjspx
    0.63
     autorytatywna
    0.63
     acceptez
    0.61
     surla
    0.60
    tvguidetime
    0.60
    SBATCH
    0.60
    ScopeManager
    0.60
     Wicidata
    0.59
     EconPapers
    0.57
    Act Density 0.006%

    No Known Activations