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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements and scientific parameters

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

    Numbers followed by "to" or "from"

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    */;
    -0.56
    ']->
    -0.55
    */)
    -0.52
    fährt
    -0.51
    "]:
    -0.51
     sem
    -0.50
     </
    -0.50
    </th>
    -0.50
    </h6>
    -0.50
     tre
    -0.49
    POSITIVE LOGITS
    middels
    0.75
    ㅡ
    0.68
    0.67
    ㅗ
    0.65
     greateſt
    0.64
     Eſ
    0.63
    PhysRevLett
    0.63
     satria
    0.62
    culously
    0.62
    kuuta
    0.62
    Act Density 0.061%

    No Known Activations