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

    Neuronpedia

    INDEX
    Explanations

    Circuit connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    限
    -0.07
    šti
    -0.07
    濃
    -0.06
    涉
    -0.06
    ikk
    -0.06
    xx
    -0.06
    ugin
    -0.06
     إل
    -0.06
    _hop
    -0.06
     swath
    -0.06
    POSITIVE LOGITS
     ale
    0.08
     código
    0.07
    temperature
    0.06
    (encoded
    0.06
    _filepath
    0.06
    /back
    0.06
     seamless
    0.06
    .FromArgb
    0.06
     DOM
    0.06
    RouterModule
    0.06
    Act Density 0.035%

    No Known Activations