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

    Neuronpedia

    INDEX
    Explanations

    references to numerical or coded classifications

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

    legal case citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.71
    fjspx
    -0.70
    aarrggbb
    -0.67
     intStringLen
    -0.61
     surla
    -0.60
     gynhyrchwyd
    -0.58
    tanleria
    -0.56
     ſte
    -0.55
    tagHelperRunner
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    POSITIVE LOGITS
     Q
    0.33
     humanidade
    0.33
     linguagem
    0.32
    accompag
    0.30
     Nutzung
    0.29
     بهتر
    0.29
    essentiel
    0.28
     spod
    0.28
    TagMode
    0.28
     Besitz
    0.27
    Act Density 0.008%

    No Known Activations