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

    Neuronpedia

    INDEX
    Explanations

    express

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     streamlined
    -0.07
    _number
    -0.06
    [column
    -0.06
    altern
    -0.06
    _po
    -0.06
     찬
    -0.06
    Activate
    -0.06
     Developed
    -0.06
     Sanat
    -0.06
    _creator
    -0.06
    POSITIVE LOGITS
    ρός
    0.06
     renders
    0.06
     уч
    0.06
    rack
    0.06
    mathrm
    0.06
                         ↵
    0.06
     brilliantly
    0.06
    ioso
    0.06
    รรม
    0.06
    ("↵
    0.06
    Act Density 0.006%

    No Known Activations