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

    Neuronpedia

    INDEX
    Explanations

    referring to others' words/ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buildFor
    0.49
    नए
    0.47
    的选择
    0.46
    utile
    0.42
    Thank
    0.42
    That
    0.42
    通过
    0.42
    Լ
    0.42
    为
    0.41
    信息的
    0.41
    POSITIVE LOGITS
     kein
    0.48
     például
    0.48
     esimerkiksi
    0.47
     geen
    0.47
     keine
    0.45
    စ္စည်း
    0.45
     ebenfalls
    0.45
     keinen
    0.44
     zog
    0.43
     eingesch
    0.43
    Act Density 0.006%

    No Known Activations