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

    Neuronpedia

    INDEX
    Explanations

    complex numerical codes or identifiers within the text

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

    Hexadecimal and similar codes

    np_acts-logits-general · gemini-2.0-flash

    code and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.78
    IntoConstraints
    -0.74
     informée
    -0.72
    iterranée
    -0.71
     ſei
    -0.71
    makeConstraints
    -0.71
     lenker
    -0.69
    extAlignment
    -0.68
     EconPapers
    -0.68
     NSCoder
    -0.67
    POSITIVE LOGITS
    
    0.61
     Pfeiffer
    0.36
    7
    0.33
     Lenz
    0.31
     Nilsson
    0.31
     bad
    0.30
     얻
    0.30
     './../
    0.28
     twice
    0.28
     Osten
    0.28
    Act Density 0.051%

    No Known Activations