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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables in structured formats

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

    mathematical notation with E and tr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ":[{
    -0.49
    RepeatedField
    -0.44
    rfloor
    -0.42
    )}</
    -0.42
     dikem
    -0.42
    delaide
    -0.42
    onAttach
    -0.42
    baliknya
    -0.41
    adopt
    -0.41
     krzy
    -0.41
    POSITIVE LOGITS
    TokenNameLBRACE
    0.47
     Gerechtigkeit
    0.43
     vinaigre
    0.42
    tinta
    0.41
    GEBURTSDATUM
    0.40
    pgsql
    0.40
    CascadeType
    0.39
    Networking
    0.39
     borda
    0.38
     Insgesamt
    0.38
    Act Density 0.127%

    No Known Activations