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

    Neuronpedia

    INDEX
    Explanations

    notations or formatting elements within the text

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

    language codes or user prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſicht
    -1.00
     queſta
    -1.00
     ſch
    -0.98
    <unused16>
    -0.96
    <unused8>
    -0.96
    [@BOS@]
    -0.96
    <unused41>
    -0.96
    <unused43>
    -0.96
    <unused74>
    -0.96
    <pad>
    -0.96
    POSITIVE LOGITS
    ↵
    0.56
    1
    0.43
    _
    0.42
            
    0.42
    2
    0.41
        
    0.40
    .
    0.40
    S
    0.38
    0.37
    *
    0.36
    Act Density 0.000%

    No Known Activations