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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Truthy
    -0.08
     Dong
    -0.07
    'C
    -0.06
     Luo
    -0.06
    python
    -0.06
     JScrollPane
    -0.06
     Levi
    -0.06
    BLEM
    -0.06
    -order
    -0.06
     Stanton
    -0.06
    POSITIVE LOGITS
     разв
    0.07
    ccak
    0.06
     وی
    0.06
     Од
    0.06
     kuv
    0.06
    .barDockControl
    0.06
    और
    0.06
    azing
    0.06
     سود
    0.06
     ASD
    0.06
    Act Density 0.001%

    No Known Activations