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
    assembly
    -0.06
     vibrant
    -0.06
     programmer
    -0.06
    cn
    -0.06
     classNames
    -0.06
    _profiles
    -0.06
    说
    -0.05
     loc
    -0.05
     literary
    -0.05
    order
    -0.05
    POSITIVE LOGITS
    _NOTICE
    0.07
    ΙΑΚ
    0.07
     성공
    0.07
    ़ों
    0.07
     trespass
    0.06
    ्रव
    0.06
    .credit
    0.06
    AILS
    0.06
    Ó
    0.06
    WebResponse
    0.06
    Act Density 0.004%

    No Known Activations