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

    Neuronpedia

    INDEX
    Explanations

    https

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apeake
    -0.06
    nger
    -0.06
     storyt
    -0.06
    exampleModalLabel
    -0.06
    arrow
    -0.06
     dependable
    -0.06
    ör
    -0.06
    uu
    -0.06
     --------------------
    -0.06
     Arrow
    -0.05
    POSITIVE LOGITS
     oyn
    0.07
    .stderr
    0.07
     Ebay
    0.07
    .FileName
    0.07
     saturation
    0.06
     whistle
    0.06
     yeniden
    0.06
    śmy
    0.06
     wrink
    0.06
     ува
    0.06
    Act Density 0.001%

    No Known Activations