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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with various operators and functions

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

    Mathematical expressions with exponents

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.61
    Autoritní
    -0.57
     Roskov
    -0.54
     Walkover
    -0.53
    Билгалдахарш
    -0.49
     CHtml
    -0.49
     Meksiku
    -0.49
    verwijspagina
    -0.48
    лтемелер
    -0.48
     ✭✭
    -0.47
    POSITIVE LOGITS
    >+</
    0.57
    }+\
    0.52
     +\
    0.50
     +
    0.49
    +</
    0.48
    +\
    0.47
    WriteTagHelper
    0.47
    tagHelperRunner
    0.46
     +=
    0.46
    )+\
    0.46
    Act Density 0.959%

    No Known Activations