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

    Neuronpedia

    INDEX
    Explanations

    being startled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坐在
    -0.07
     Shack
    -0.06
    ся
    -0.06
    beg
    -0.06
    κέ
    -0.06
     memnun
    -0.06
     epic
    -0.06
    це
    -0.06
     تازه
    -0.06
    Path
    -0.06
    POSITIVE LOGITS
     startling
    0.08
     startled
    0.07
     Dut
    0.07
    áli
    0.07
     inputs
    0.06
    toInt
    0.06
    start
    0.06
     Al
    0.06
     adını
    0.06
    .ResponseEntity
    0.06
    Act Density 0.016%

    No Known Activations