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

    Neuronpedia

    INDEX
    Explanations

    ){

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aub
    -0.07
    ONDON
    -0.06
    �
    -0.06
     Ald
    -0.06
    vert
    -0.06
    ило
    -0.06
     payment
    -0.06
    ло
    -0.06
    olutions
    -0.06
     Perhaps
    -0.06
    POSITIVE LOGITS
    sci
    0.07
     Dynamics
    0.07
    \"";↵
    0.07
     dayan
    0.07
     这
    0.07
    _mentions
    0.07
     Diamond
    0.07
    _CANCEL
    0.07
    .Entities
    0.06
    rika
    0.06
    Act Density 0.002%

    No Known Activations