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

    Neuronpedia

    INDEX
    Explanations

    grow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پست
    -0.07
     teamed
    -0.07
    ��
    -0.06
     बद
    -0.06
    計劃
    -0.06
    .weight
    -0.06
    <fieldset
    -0.06
     그림
    -0.06
     privileges
    -0.06
    坪
    -0.06
    POSITIVE LOGITS
    'class
    0.07
    >Email
    0.06
     Michelle
    0.06
    Michelle
    0.06
     indispens
    0.06
    _Check
    0.06
     KY
    0.06
     comet
    0.06
     Trường
    0.06
    ANEL
    0.06
    Act Density 0.011%

    No Known Activations