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

    Neuronpedia

    INDEX
    Explanations

    suspected data breach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。.
    0.43
     بدا
    0.41
    −</
    0.40
    ;&
    0.39
    Demand
    0.39
    Qualifications
    0.38
    Stability
    0.38
    Authority
    0.38
     موضوع
    0.38
     intuitively
    0.38
    POSITIVE LOGITS
     cous
    0.43
     llamado
    0.43
    ता
    0.41
     haka
    0.40
     veloce
    0.38
     Hod
    0.37
     Zal
    0.37
     AEC
    0.36
     Scor
    0.36
     leg
    0.36
    Act Density 0.000%

    No Known Activations