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

    Neuronpedia

    INDEX
    Explanations

    Independence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    representation
    -0.06
     Rubber
    -0.06
    tar
    -0.06
     الاجتماع
    -0.06
     الرم
    -0.05
     CLK
    -0.05
     cos
    -0.05
    できます
    -0.05
     besch
    -0.05
     Za
    -0.05
    POSITIVE LOGITS
     ethanol
    0.08
    unnable
    0.07
    ився
    0.07
    Improved
    0.07
    acking
    0.07
    ERC
    0.07
     süreç
    0.06
     onPostExecute
    0.06
    ibox
    0.06
    �
    0.06
    Act Density 0.006%

    No Known Activations