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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dinosaurs
    -0.07
     늘
    -0.07
    CUDA
    -0.07
    ml
    -0.07
    /users
    -0.07
    的是
    -0.07
     stuff
    -0.07
    processor
    -0.06
    594
    -0.06
    도로
    -0.06
    POSITIVE LOGITS
     touching
    0.07
     Archer
    0.07
    .black
    0.07
     fieldName
    0.06
     Jakarta
    0.06
    Candidates
    0.06
    asion
    0.06
    Feat
    0.06
     Hos
    0.06
    pike
    0.05
    Act Density 0.026%

    No Known Activations