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

    Neuronpedia

    INDEX
    Explanations

    demonstrated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    源
    -0.07
     相
    -0.07
     توسط
    -0.07
    相
    -0.07
    ↵
    -0.06
    algorithm
    -0.06
     články
    -0.06
    Clazz
    -0.06
     Fault
    -0.06
     tom
    -0.06
    POSITIVE LOGITS
    combined
    0.07
    cho
    0.06
     PO
    0.06
     negotiating
    0.06
     зап
    0.06
    madı
    0.06
    .Free
    0.06
    คร
    0.06
    IGN
    0.06
     SAP
    0.06
    Act Density 0.037%

    No Known Activations