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

    Neuronpedia

    INDEX
    Explanations

    academic research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scholar
    -1.10
    Scholar
    -0.75
    GetEnumerator
    -0.66
    ंदीखरीदारी
    -0.65
     snippetHide
    -0.65
    DockStyle
    -0.61
    WireFormat
    -0.57
    JvmStatic
    -0.57
    цездатний
    -0.57
     SafeMath
    -0.56
    POSITIVE LOGITS
    ly
    1.00
    🏼
    0.73
    ity
    0.72
    ry
    0.72
    LY
    0.69
    🏽
    0.67
    liness
    0.65
    🏻
    0.64
    ize
    0.60
    fully
    0.56
    Act Density 1.528%

    No Known Activations