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

    Neuronpedia

    INDEX
    Explanations

    requests and prompts related to coding or technical instructions.

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.31
     ث
    0.30
     لم
    0.30
    ه
    0.28
     cryptographic
    0.28
     obscures
    0.27
     delimiters
    0.26
     encapsulation
    0.25
     concatenation
    0.25
    р
    0.25
    POSITIVE LOGITS
     be
    0.41
     have
    0.36
     make
    0.34
     provide
    0.32
     give
    0.31
     do
    0.30
     improve
    0.30
     keep
    0.29
     organize
    0.29
     put
    0.28
    Act Density 0.852%

    No Known Activations