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

    Neuronpedia

    INDEX
    Explanations

    numbers, particularly in various formats or representations

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

    mathematical expressions, variables, lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.53
    coln
    -0.52
    feld
    -0.51
     Jab
    -0.50
     defStyle
    -0.49
    ffffffff
    -0.49
    ểu
    -0.49
    脚注
    -0.48
     limitation
    -0.48
     Wör
    -0.47
    POSITIVE LOGITS
    __':
    0.65
     betweenstory
    0.62
    MessageTagHelper
    0.60
     ISNI
    0.59
     MainAxisSize
    0.59
    cmath
    0.57
     NSCoder
    0.57
    __":
    0.57
    økt
    0.57
    ()]);
    0.57
    Act Density 0.411%

    No Known Activations