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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and software development

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

    After a period in brackets

    np_acts-logits-general · gemini-2.0-flash

    utility and test code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    -0.29
     pracov
    -0.28
     Lösungs
    -0.27
     největ
    -0.25
     lamang
    -0.25
     způ
    -0.25
    awaiter
    -0.25
     kanyang
    -0.24
     própria
    -0.24
     an
    -0.24
    POSITIVE LOGITS
    featureID
    0.82
     ་་
    0.73
    таратура
    0.72
    ロウィン
    0.71
    <unused41>
    0.71
    [@BOS@]
    0.71
    <unused47>
    0.71
     témoig
    0.71
    <unused52>
    0.71
    <unused3>
    0.70
    Act Density 0.444%

    No Known Activations