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

    Neuronpedia

    INDEX
    Explanations

    explanations that reference reasons or justifications

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

    introducing causal clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.52
    ValueGenerated
    -0.50
    esModule
    -0.49
    httphttps
    -0.49
    :✨
    -0.46
     vac
    -0.44
    FromNib
    -0.43
     Ordin
    -0.43
     Bantu
    -0.42
    encodeWith
    -0.42
    POSITIVE LOGITS
     fordi
    0.40
     Administrativna
    0.39
    because
    0.38
    否
    0.36
    Obfuscated
    0.34
    porque
    0.34
     perché
    0.34
    因为
    0.34
    因为他
    0.34
     perchè
    0.34
    Act Density 0.138%

    No Known Activations