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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mistakes
    -0.07
    есь
    -0.07
    OwnerId
    -0.07
     Places
    -0.07
     Place
    -0.06
     war
    -0.06
     sinking
    -0.06
    (indexPath
    -0.06
     Pik
    -0.06
     lying
    -0.06
    POSITIVE LOGITS
    čů
    0.07
    .DIS
    0.07
    ксп
    0.06
    HONE
    0.06
    uably
    0.06
    .pk
    0.06
    Ģ
    0.06
    .INTER
    0.06
    .am
    0.06
    atchewan
    0.06
    Act Density 0.009%

    No Known Activations