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

    Neuronpedia

    INDEX
    Explanations

    Paris

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clan
    -0.07
     helf
    -0.07
    ENTIAL
    -0.07
    /problems
    -0.06
    τηγορία
    -0.06
    obo
    -0.06
    codile
    -0.06
     Bubble
    -0.06
    designation
    -0.06
    eliminar
    -0.06
    POSITIVE LOGITS
     Paris
    0.20
    Paris
    0.15
     paris
    0.08
     Rolling
    0.07
    �
    0.07
    air
    0.07
    _SECURE
    0.07
    asic
    0.07
    ....↵↵
    0.07
     Months
    0.07
    Act Density 0.004%

    No Known Activations