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

    Neuronpedia

    INDEX
    Explanations

    initial state or question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addicts
    0.44
     Kraj
    0.42
     対象
    0.40
     Squid
    0.40
     Shape
    0.40
     Saeed
    0.40
     Seek
    0.40
     کھیلیں
    0.39
     Bring
    0.39
     forth
    0.39
    POSITIVE LOGITS
    izable
    0.46
    inated
    0.43
     pergunta
    0.42
    いましたが
    0.42
     erroneously
    0.41
    izante
    0.41
    ality
    0.41
    hedral
    0.41
    inguishing
    0.40
    ized
    0.40
    Act Density 0.012%

    No Known Activations