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

    Neuronpedia

    INDEX
    Explanations

    performance magic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uint
    -0.07
    (method
    -0.07
     bloss
    -0.07
     TV
    -0.06
     blossom
    -0.06
    (gray
    -0.06
     โ
    -0.06
     vznik
    -0.06
    (rp
    -0.06
    (_
    -0.06
    POSITIVE LOGITS
     Override
    0.07
     multiplication
    0.07
    finish
    0.06
    straints
    0.06
     apo
    0.06
    itioner
    0.06
    Britain
    0.06
    isper
    0.06
     cít
    0.06
    17
    0.06
    Act Density 0.046%

    No Known Activations