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

    Neuronpedia

    INDEX
    Explanations

    become

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	RT
    -0.07
     Edwards
    -0.07
     centroids
    -0.06
     machine
    -0.06
    、い
    -0.06
     pods
    -0.06
    ,str
    -0.06
    $is
    -0.06
     đẩy
    -0.06
     жовтня
    -0.06
    POSITIVE LOGITS
    نا
    0.07
    dT
    0.07
    _plan
    0.07
     wholes
    0.06
     ordinances
    0.06
    止
    0.06
     pochop
    0.06
    rition
    0.06
     musica
    0.06
    atio
    0.06
    Act Density 0.023%

    No Known Activations