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

    Neuronpedia

    INDEX
    Explanations

    legal and licensing terminology in software documentation

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

    Code-related licensing and copyright information

    np_acts-logits-general · gemini-2.0-flash

    http://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.35
     şöyle
    -0.27
     keseluruhan
    -0.24
     ویکی‌آمباردا
    -0.24
     poderes
    -0.23
    :
    -0.21
    ierend
    -0.20
     dışında
    -0.20
     diaria
    -0.20
     beschik
    -0.20
    POSITIVE LOGITS
     dieſen
    0.99
     dieſer
    0.97
     Weiſe
    0.95
    <unused8>
    0.94
    <unused41>
    0.94
    <unused3>
    0.94
    <unused74>
    0.94
     zwiſchen
    0.94
    <unused52>
    0.94
    [@BOS@]
    0.94
    Act Density 0.340%

    No Known Activations