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

    Neuronpedia

    INDEX
    Explanations

    Letter Sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fifo
    -0.06
    belongs
    -0.06
     alignments
    -0.06
    thren
    -0.06
    .focus
    -0.06
     bearer
    -0.05
     whites
    -0.05
    _ord
    -0.05
    .getcwd
    -0.05
     obs
    -0.05
    POSITIVE LOGITS
     Республи
    0.07
    ▍▍▍▍
    0.07
    _flow
    0.07
    )↵↵↵
    0.07
    官方
    0.06
    ())↵↵↵
    0.06
    Flow
    0.06
     ↵  ↵
    0.06
     birthday
    0.06
     hlad
    0.06
    Act Density 0.002%

    No Known Activations