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

    Neuronpedia

    INDEX
    Explanations

    learning happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     алюми
    0.44
    cherche
    0.41
    striatis
    0.41
     algéb
    0.41
    Stokes
    0.41
    யூ
    0.41
    aun
    0.41
    ARIOS
    0.41
     солне
    0.40
     circunfer
    0.40
    POSITIVE LOGITS
     The
    0.50
     CPU
    0.45
     ہوتا
    0.45
     PSD
    0.43
    この
    0.42
     recruiter
    0.42
     됩니다
    0.41
    成为
    0.40
     hiring
    0.40
     Recruiting
    0.39
    Act Density 0.004%

    No Known Activations