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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _def
    -0.06
    政策
    -0.06
     nx
    -0.06
     gul
    -0.06
    Deg
    -0.06
    Brit
    -0.06
    (bin
    -0.06
    _stride
    -0.06
    Native
    -0.06
    τρα
    -0.06
    POSITIVE LOGITS
     imkân
    0.07
     Kültür
    0.07
     anak
    0.07
    _LOAD
    0.07
     morb
    0.06
     mám
    0.06
     kültür
    0.06
    造成
    0.06
     valves
    0.06
    ený
    0.06
    Act Density 0.000%

    No Known Activations