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

    Neuronpedia

    INDEX
    Explanations

    quoted speech, dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     particolarmente
    0.49
     teorema
    0.48
     theorem
    0.44
     pogled
    0.44
     privati
    0.44
     analisi
    0.43
     direttamente
    0.42
     vain
    0.42
     prezzi
    0.42
     estremamente
    0.42
    POSITIVE LOGITS
     Allow
    0.47
     में
    0.46
    Allow
    0.46
    猷
    0.46
    发生
    0.44
     SSO
    0.44
     Afr
    0.42
     هيا
    0.42
    排序
    0.42
     Vire
    0.42
    Act Density 0.108%

    No Known Activations