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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smarter
    -0.08
    Cab
    -0.06
     Pastor
    -0.06
    groupid
    -0.06
     başarılı
    -0.06
    าคาร
    -0.06
    gt
    -0.06
    己
    -0.06
     clothes
    -0.06
    .hadoop
    -0.06
    POSITIVE LOGITS
    <form
    0.06
    _video
    0.06
    iể
    0.06
    (vertices
    0.06
    -elect
    0.06
     değer
    0.06
    UN
    0.06
     indirect
    0.06
     valueType
    0.06
     truths
    0.06
    Act Density 0.034%

    No Known Activations