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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Err
    -0.06
    Theta
    -0.06
     рыб
    -0.06
     demands
    -0.06
     continues
    -0.06
    .csv
    -0.06
    ันทร
    -0.06
    Decimal
    -0.06
     University
    -0.06
    =model
    -0.06
    POSITIVE LOGITS
    واع
    0.07
    	hr
    0.07
    )Math
    0.06
    练
    0.06
    ');?>"
    0.06
     uso
    0.06
     Ash
    0.06
    	get
    0.06
     حضرت
    0.06
     داخل
    0.06
    Act Density 0.004%

    No Known Activations