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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ethics
    -0.07
    XPath
    -0.07
    Ya
    -0.07
     Formatting
    -0.07
    _SPEC
    -0.06
    Yaw
    -0.06
    efa
    -0.06
     đảng
    -0.06
    orraine
    -0.06
    InParameter
    -0.06
    POSITIVE LOGITS
     고
    0.07
     sağlay
    0.07
    πα
    0.06
    练
    0.06
     interconnected
    0.06
     //////////////////////////////////////////////////////////////////////
    0.06
     universally
    0.06
     جمله
    0.06
    _compiler
    0.06
    _leader
    0.06
    Act Density 0.017%

    No Known Activations