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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references

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

    Code, math, or comparison operators

    np_acts-logits-general · gemini-2.0-flash

    return true; return false;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.53
    TintMode
    -0.43
    DockStyle
    -0.39
    fromCharCode
    -0.39
    XmlAccessType
    -0.37
    geos
    -0.36
    wark
    -0.36
    agisse
    -0.36
    delwed
    -0.35
    hun
    -0.35
    POSITIVE LOGITS
     przecież
    0.51
     antemano
    0.50
     protectora
    0.50
    曖昧さ回避
    0.48
     gleichzeitig
    0.45
     trotzdem
    0.44
     simultaneously
    0.44
     contradictory
    0.44
    __":
    0.42
    مصادر
    0.42
    Act Density 1.438%

    No Known Activations