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

    Neuronpedia

    INDEX
    Explanations

    pre/pred

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trenches
    -0.07
     nunca
    -0.07
     Literature
    -0.06
     Locker
    -0.06
    ために
    -0.06
    .ep
    -0.06
    Aux
    -0.06
    ör
    -0.06
    旅游
    -0.06
     أك
    -0.06
    POSITIVE LOGITS
     Mime
    0.06
     asyncio
    0.06
     warranties
    0.06
     opc
    0.06
    osci
    0.06
    [axis
    0.06
     derog
    0.06
     gỗ
    0.06
    ycopg
    0.06
    unset
    0.06
    Act Density 0.005%

    No Known Activations