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

    Neuronpedia

    INDEX
    Explanations

    booking flights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poo
    -0.07
    Race
    -0.06
     lad
    -0.06
    "h
    -0.06
    iado
    -0.06
    computer
    -0.06
     soudu
    -0.06
     knob
    -0.06
     خور
    -0.06
    -col
    -0.06
    POSITIVE LOGITS
    URATION
    0.07
    迪
    0.07
    플
    0.07
     ALIGN
    0.07
    .Bytes
    0.07
     inputData
    0.06
     Rift
    0.06
     رشد
    0.06
     prote
    0.06
    _None
    0.06
    Act Density 0.010%

    No Known Activations