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

    Neuronpedia

    INDEX
    Explanations

    email and social media handles or mentions

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

    documentation tags or conversational markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.96
    ロウィン
    -0.90
    ðsíða
    -0.88
    ſſung
    -0.88
    Personendaten
    -0.87
    TemporalType
    -0.85
    <unused79>
    -0.85
    <unused43>
    -0.85
    <unused8>
    -0.85
    <unused16>
    -0.85
    POSITIVE LOGITS
     @
    0.73
    @
    0.48
     
    0.47
    <h2>
    0.42
     #
    0.39
     (
    0.39
    #
    0.37
     (@
    0.37
     '
    0.37
      
    0.37
    Act Density 0.000%

    No Known Activations