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

    Neuronpedia

    INDEX
    Explanations

    technical implementation, initial steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FromString
    1.22
    ご紹介
    1.18
    umption
    1.13
     inici
    1.12
    က
    1.10
    FUENTE
    1.10
     empat
    1.09
    gister
    1.09
     ause
    1.08
     embassy
    1.07
    POSITIVE LOGITS
     doğ
    1.20
    هو
    1.09
    и
    1.09
     düş
    1.08
    та
    1.01
    o
    1.01
    ಹ
    1.00
    よう
    1.00
     Wszyst
    0.99
    =""
    0.99
    Act Density 0.000%

    No Known Activations