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

    Neuronpedia

    INDEX
    Explanations

    terms related to software components and data management

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.04
    LookAnd
    -1.02
    <unused14>
    -1.01
    <unused41>
    -1.01
    <unused42>
    -1.00
    <unused28>
    -1.00
    <unused52>
    -1.00
    <unused79>
    -1.00
    <unused74>
    -1.00
    [@BOS@]
    -1.00
    POSITIVE LOGITS
    .
    0.27
    land
    0.23
    IN
    0.23
     AS
    0.23
    in
    0.21
     ans
    0.21
    ↵
    0.20
    nya
    0.20
    ARS
    0.20
     $\
    0.20
    Act Density 0.000%

    No Known Activations