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
     sighed
    -0.07
     látky
    -0.06
     hoop
    -0.06
     травня
    -0.06
     Hải
    -0.06
     �
    -0.06
     Mount
    -0.06
     �
    -0.06
    ,right
    -0.06
     Buttons
    -0.06
    POSITIVE LOGITS
    .stock
    0.07
    ैठक
    0.07
     tetas
    0.06
     clubhouse
    0.06
     Milwaukee
    0.06
    Thomas
    0.06
     ніч
    0.06
    utzer
    0.06
    **:
    0.06
    names
    0.06
    Act Density 0.000%

    No Known Activations