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

    Neuronpedia

    INDEX
    Explanations

    percentages and their variations

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

    numbers followed by percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.56
    原始内容存档于
    -0.55
     MainAxisSize
    -0.47
    いしい
    -0.43
    csolódó
    -0.43
    databind
    -0.42
    bleau
    -0.41
    \{\\
    -0.41
     الرياضيه
    -0.40
     Construct
    -0.40
    POSITIVE LOGITS
    %
    1.66
     \%$
    1.48
     %
    1.33
    \%
    1.26
    ]%
    1.23
     \%}$
    1.16
     $\%$
    1.16
     \%
    1.16
    )%
    1.15
     percent
    1.14
    Act Density 0.101%

    No Known Activations