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

    Neuronpedia

    INDEX
    Explanations

    bib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hazard
    -0.06
     girdi
    -0.06
    다면
    -0.06
    .UserId
    -0.06
    .instructions
    -0.06
     tuz
    -0.06
     human
    -0.06
    iêu
    -0.06
     masks
    -0.06
    Sit
    -0.06
    POSITIVE LOGITS
     Experts
    0.07
     Pine
    0.06
    Interface
    0.06
    undai
    0.06
    syntax
    0.06
    Sorting
    0.06
    dealer
    0.06
    -syntax
    0.06
    ondheim
    0.06
    pot
    0.06
    Act Density 0.005%

    No Known Activations