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

    Neuronpedia

    INDEX
    Explanations

    instances of specific formatting or notation, such as brackets and ellipses

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

    omission markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.57
    Autoritní
    -0.51
    出版年
    -0.50
     صوتيه
    -0.48
     oprot
    -0.47
    ConstraintMaker
    -0.47
     linkovi
    -0.46
    Hentet
    -0.45
    olera
    -0.44
     noDo
    -0.43
    POSITIVE LOGITS
    …
    0.42
     …
    0.39
    中略
    0.39
    ...
    0.38
    gelopen
    0.37
     ...
    0.37
    ……
    0.36
    0.35
    yi
    0.34
    ......
    0.33
    Act Density 0.119%

    No Known Activations