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

    Neuronpedia

    INDEX
    Explanations

    dual and infinitives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alee
    0.55
    ’
    0.49
    er
    0.49
    rones
    0.45
    ista
    0.45
    jid
    0.43
    ollo
    0.42
    lk
    0.42
     Matsuda
    0.42
    น
    0.42
    POSITIVE LOGITS
     второго
    0.50
     неделю
    0.49
     יותר
    0.47
     у
    0.46
     неко
    0.46
     miesią
    0.46
     trasport
    0.45
     débat
    0.45
     প্রশাস
    0.45
    Questa
    0.45
    Act Density 0.003%

    No Known Activations