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

    Neuronpedia

    INDEX
    Explanations

    Document contents/analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    면
    -0.08
    NON
    -0.07
    NOP
    -0.07
    .Nil
    -0.07
    PRS
    -0.07
    ╤
    -0.07
    Frank
    -0.07
    |.
    -0.07
    Hal
    -0.07
    ?type
    -0.07
    POSITIVE LOGITS
    .Language
    0.07
    tività
    0.07
    扎根
    0.07
    actoring
    0.06
    à
    0.06
     BOTH
    0.06
    (PARAM
    0.06
    Partition
    0.06
    Compact
    0.06
    object
    0.06
    Act Density 0.107%

    No Known Activations