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

    Neuronpedia

    INDEX
    Explanations

    numerical representations or symbols related to data and statistics

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

    structural delimiters and foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.55
    ↵↵
    -0.53
    ″]
    -0.52
    ↵↵↵
    -0.52
    ↵
    -0.51
     Administrativna
    -0.50
    AnimationsModule
    -0.47
    endphp
    -0.46
     مشين
    -0.46
    נטרנט
    -0.46
    POSITIVE LOGITS
     entanto
    0.49
    wußt
    0.42
     pouvoit
    0.40
     auroit
    0.40
    antaranya
    0.40
     Grüsse
    0.38
     berço
    0.38
     avoient
    0.38
    ParallelGroup
    0.38
     ști
    0.38
    Act Density 0.030%

    No Known Activations