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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and probability-related terms

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

    Picking letters without replacement, probability calculations

    np_acts-logits-general · gemini-2.0-flash

    probability of picking without replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bkz
    -0.58
    甚至是
    -0.55
    Meski
    -0.55
     prácticamente
    -0.53
     Meski
    -0.52
    —“
    -0.52
    Literally
    -0.51
    Wherever
    -0.51
    Bahkan
    -0.51
     Ngoài
    -0.51
    POSITIVE LOGITS
     Suppose
    0.78
     $\$
    0.76
     Assume
    0.75
    ​=
    0.75
    ​
    0.71
    '$
    0.71
     переписи
    0.68
     سكانية
    0.67
    $\%$
    0.67
     $=
    0.67
    Act Density 1.683%

    No Known Activations