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

    Neuronpedia

    INDEX
    Explanations

    trap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voltage
    -0.07
     gou
    -0.07
     BW
    -0.07
     Cic
    -0.07
    initialize
    -0.06
    üle
    -0.06
     Dean
    -0.06
     intensity
    -0.06
     Wilde
    -0.06
     swelling
    -0.06
    POSITIVE LOGITS
     Trap
    0.10
     trap
    0.09
     strap
    0.07
     Lopez
    0.07
     traps
    0.07
    spy
    0.07
     Strap
    0.07
    】,
    0.07
    ,state
    0.07
    аток
    0.06
    Act Density 0.005%

    No Known Activations