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

    Neuronpedia

    INDEX
    Explanations

    comma usage in programming syntax

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sünde
    -0.40
     Begründung
    -0.39
    tgz
    -0.38
     śmierci
    -0.38
     Annahme
    -0.38
    ywna
    -0.38
     Sünden
    -0.37
     honra
    -0.36
     kematian
    -0.36
     Lizenz
    -0.36
    POSITIVE LOGITS
     لينك
    0.56
     nakalista
    0.52
    oneofs
    0.51
    المناصب
    0.51
    iſen
    0.50
    Centa
    0.47
    Clifford
    0.47
     ſind
    0.47
     uParam
    0.46
    schon
    0.46
    Act Density 0.020%

    No Known Activations