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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions or equations involving roots and their properties

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

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.34
    ロウィン
    -1.27
    ſchaft
    -1.25
    ſicht
    -1.24
    niſſe
    -1.23
    ſſung
    -1.21
    <unused14>
    -1.20
    <unused16>
    -1.20
    <unused8>
    -1.20
    [@BOS@]
    -1.20
    POSITIVE LOGITS
    I
    0.56
        
    0.55
    0.55
    _
    0.55
    (
    0.54
    The
    0.52
                
    0.50
            
    0.49
    2
    0.49
                    
    0.48
    Act Density 0.026%

    No Known Activations