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

    Neuronpedia

    INDEX
    Explanations

    Appearance or impression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flush
    -0.07
     synagogue
    -0.06
     learnt
    -0.06
     hides
    -0.06
    웠
    -0.06
    iz
    -0.06
    .visibility
    -0.06
    ennessee
    -0.06
     grandma
    -0.06
    .clock
    -0.06
    POSITIVE LOGITS
     KeyError
    0.07
    .UseText
    0.07
     Difference
    0.07
    maint
    0.07
    �
    0.07
     entitled
    0.06
     Ihrem
    0.06
    $product
    0.06
     Reduce
    0.06
    "=>
    0.06
    Act Density 0.070%

    No Known Activations