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

    Neuronpedia

    INDEX
    Explanations

    certification validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرجل
    0.40
    Between
    0.38
    選手権
    0.35
    婢
    0.34
    紳
    0.34
     Between
    0.33
    Because
    0.33
     केमिस्ट्री
    0.33
    While
    0.33
     ஆண்கள்
    0.33
    POSITIVE LOGITS
     certification
    0.52
    certification
    0.48
     certific
    0.47
     certifications
    0.46
     Zert
    0.42
    rtc
    0.39
     certificat
    0.38
    Certification
    0.38
     Certification
    0.37
     biodegradation
    0.37
    Act Density 0.000%

    No Known Activations