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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scouts
    -0.07
     �
    -0.07
    守
    -0.06
    اوی
    -0.06
    fwrite
    -0.06
     всем
    -0.06
    physics
    -0.06
    海外
    -0.06
    вей
    -0.06
     datos
    -0.06
    POSITIVE LOGITS
     Excel
    0.07
    Best
    0.06
    {x
    0.06
    IONS
    0.06
    /backend
    0.06
     psycho
    0.06
    -H
    0.06
     Ass
    0.06
     MessageType
    0.06
    ают
    0.06
    Act Density 0.002%

    No Known Activations