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

    Neuronpedia

    INDEX
    Explanations

    class and method definitions in programming code

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

    class names and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.54
     rolling
    -0.36
     joins
    -0.33
    Sigue
    -0.33
     join
    -0.32
     Join
    -0.31
    去的
    -0.31
    
    -0.31
    あたり
    -0.31
     rolls
    -0.30
    POSITIVE LOGITS
    ſicht
    0.60
     Crusoe
    0.56
    ushman
    0.55
     publiques
    0.54
     Huguen
    0.54
     nahilalakip
    0.54
    urfs
    0.53
     ſie
    0.51
     pubblici
    0.51
    HasForeignKey
    0.50
    Act Density 0.013%

    No Known Activations