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

    Neuronpedia

    INDEX
    Explanations

    disables/disable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    禟
    0.50
     Rheumat
    0.49
     Acids
    0.48
     فريبيس
    0.47
     কাঁ
    0.46
     épais
    0.46
     Vegan
    0.46
     metode
    0.45
     Severity
    0.45
     Neander
    0.45
    POSITIVE LOGITS
    Beijing
    0.63
     wireless
    0.62
     uplink
    0.62
     downlink
    0.62
     wirelessly
    0.59
    China
    0.59
    wireless
    0.59
    通信
    0.58
     VoIP
    0.57
     audio
    0.57
    Act Density 0.001%

    No Known Activations