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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fields
    -0.07
    لس
    -0.07
    ститу
    -0.06
    This
    -0.06
    θο
    -0.06
    těz
    -0.06
     saf
    -0.06
    really
    -0.06
    fields
    -0.06
     pageNo
    -0.06
    POSITIVE LOGITS
     вой
    0.07
    999
    0.06
    Wolf
    0.06
    Pipeline
    0.06
    PRESS
    0.06
     TTC
    0.06
    �
    0.06
     Total
    0.06
     thermometer
    0.06
    .Execute
    0.06
    Act Density 0.053%

    No Known Activations