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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анси
    -0.07
    iangle
    -0.07
     '#{
    -0.07
     shim
    -0.06
     doesnt
    -0.06
     yarı
    -0.06
    -valu
    -0.06
     брос
    -0.06
     κου
    -0.06
     τι
    -0.06
    POSITIVE LOGITS
    (os
    0.07
    력
    0.07
     evaluating
    0.07
    .uk
    0.06
     meddling
    0.06
    -mail
    0.06
    directory
    0.06
    (Number
    0.06
     evaluate
    0.06
     Belg
    0.06
    Act Density 0.002%

    No Known Activations