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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stevenson
    -0.07
    資
    -0.06
    .GetFileName
    -0.06
    ตะ
    -0.06
     BSP
    -0.06
     BV
    -0.06
     개발
    -0.06
     David
    -0.06
    _rd
    -0.06
     Advice
    -0.06
    POSITIVE LOGITS
    ock
    0.08
    ost
    0.07
    exels
    0.07
     isol
    0.07
    os
    0.07
    oe
    0.07
    */,
    0.07
    oop
    0.07
    iline
    0.07
     commentary
    0.07
    Act Density 0.090%

    No Known Activations