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

    Neuronpedia

    INDEX
    Explanations

    أحب، تحسين، احتياجات

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pamo
    0.44
     Machado
    0.42
     Dosage
    0.40
     Barros
    0.40
    雒
    0.39
     Permissions
    0.39
     دل
    0.39
    نائي
    0.39
    Timed
    0.38
    푀
    0.38
    POSITIVE LOGITS
     espec
    0.46
    ll
    0.45
    abol
    0.38
    ların
    0.38
    lightblue
    0.38
     ফেডার
    0.38
    sen
    0.37
     mil
    0.37
    ryn
    0.37
    ...\...\...\...\
    0.37
    Act Density 0.004%

    No Known Activations