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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical expressions and formulas

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

    math and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laſſen
    -0.99
     zoude
    -0.97
    niſſe
    -0.95
    iſen
    -0.94
    ſſung
    -0.93
    ſehen
    -0.93
    ſchaft
    -0.91
    LLocation
    -0.91
    ſicht
    -0.91
    <unused14>
    -0.91
    POSITIVE LOGITS
    0.45
    0.43
    _
    0.42
    0.41
    0.40
    0.38
                        
    0.37
        
    0.37
    ///
    0.37
            
    0.36
    Act Density 0.031%

    No Known Activations