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

    Neuronpedia

    INDEX
    Explanations

    references to schematics and diagrams

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

    schematic diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.51
    ########.
    -0.51
    UserScript
    -0.49
     FontWeight
    -0.47
    Tyr
    -0.45
    <?
    -0.44
     Tyr
    -0.44
     nitrogen
    -0.44
     consonants
    -0.43
     commas
    -0.43
    POSITIVE LOGITS
     schematic
    1.70
     Schematic
    1.62
    Schematic
    1.43
     sche
    0.75
    matics
    0.71
    示意图
    0.70
     diagram
    0.69
     Diagram
    0.69
    sche
    0.69
     ſche
    0.67
    Act Density 0.008%

    No Known Activations