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

    Neuronpedia

    INDEX
    Explanations

    Y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Washington
    -0.07
    .close
    -0.07
     fm
    -0.06
     Pandora
    -0.06
     shuffled
    -0.06
     уход
    -0.06
     韓
    -0.06
    arians
    -0.06
    โก
    -0.06
     nikdy
    -0.06
    POSITIVE LOGITS
    етель
    0.07
    Configs
    0.07
    _DST
    0.06
    öl
    0.06
    [indexPath
    0.06
    _TIMER
    0.06
    InstanceOf
    0.06
    loaded
    0.06
    .des
    0.06
    Classes
    0.06
    Act Density 0.008%

    No Known Activations