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

    Neuronpedia

    INDEX
    Explanations

    spy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deem
    -0.07
    egment
    -0.07
    ical
    -0.06
    ICAL
    -0.06
    ICA
    -0.06
     coaster
    -0.06
     NW
    -0.06
    )NSString
    -0.06
     uploaded
    -0.06
     těch
    -0.06
    POSITIVE LOGITS
     myšlen
    0.07
     spy
    0.07
    ┬
    0.06
     Spy
    0.06
     سر
    0.06
     пос
    0.06
     buddy
    0.06
    appe
    0.06
     monitor
    0.06
    .';↵
    0.06
    Act Density 0.004%

    No Known Activations