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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dejtings
    -0.07
    芷
    -0.07
    .maps
    -0.07
    lbl
    -0.07
    与时俱
    -0.07
    egend
    -0.06
    髹
    -0.06
    /inet
    -0.06
     أج
    -0.06
     nameLabel
    -0.06
    POSITIVE LOGITS
     airport
    0.07
     Sith
    0.07
    ить
    0.06
     apocalypse
    0.06
    ران
    0.06
     literal
    0.06
    __↵↵
    0.06
     Trial
    0.06
    شكر
    0.06
     //
↵
↵
    0.06
    Act Density 0.001%

    No Known Activations