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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     six
    -0.07
    ))*
    -0.07
     dört
    -0.07
     nine
    -0.06
     thirteen
    -0.06
    12
    -0.06
     three
    -0.06
    вод
    -0.06
     कप
    -0.06
    Spot
    -0.06
    POSITIVE LOGITS
     граж
    0.07
    dehyde
    0.07
    .Right
    0.06
    .abs
    0.06
    ificacion
    0.06
     hover
    0.06
     실�
    0.06
    (rad
    0.06
    الد
    0.06
     establish
    0.06
    Act Density 0.091%

    No Known Activations