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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAR
    -0.07
     умер
    -0.06
    žit
    -0.06
     toaster
    -0.06
     LOD
    -0.06
    تمر
    -0.06
     concise
    -0.06
    TRIES
    -0.06
    (Call
    -0.06
    RAR
    -0.06
    POSITIVE LOGITS
    ’ex
    0.07
     лі
    0.07
     optimizing
    0.07
    ali
    0.06
    half
    0.06
     앞
    0.06
     Diagram
    0.06
    clare
    0.06
     Registers
    0.06
    Export
    0.06
    Act Density 0.000%

    No Known Activations