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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to costs and effectiveness in different contexts

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

    comparison of quantity or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.68
     препратки
    -0.62
     ProtoMessage
    -0.58
     صوتيه
    -0.50
    AndEndTag
    -0.49
     تانيه
    -0.49
     propOrder
    -0.47
     ویکی‌پدی
    -0.47
    MathML
    -0.46
     rhestr
    -0.43
    POSITIVE LOGITS
    ตรง
    0.42
     vs
    0.39
     substitute
    0.39
     reempla
    0.39
     replace
    0.39
     Catalana
    0.38
     Ersatz
    0.38
     Replace
    0.37
     Compared
    0.37
     nicer
    0.36
    Act Density 0.099%

    No Known Activations