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

    Neuronpedia

    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .href
    -0.07
    ce
    -0.06
    _EOL
    -0.06
     Bounds
    -0.06
     ce
    -0.06
     inds
    -0.06
     praž
    -0.06
    OfWork
    -0.06
    Foo
    -0.06
     Begins
    -0.06
    POSITIVE LOGITS
    .nih
    0.06
    utely
    0.06
    (memory
    0.06
     coer
    0.06
    logan
    0.06
     dem
    0.06
     Raven
    0.06
     stern
    0.06
     Custom
    0.06
    .event
    0.06
    Act Density 0.014%

    No Known Activations