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

    Neuronpedia

    INDEX
    Explanations

    Fourier

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brid
    -0.07
    atto
    -0.06
     raft
    -0.06
    -0.06
    ]>
    -0.06
     alloy
    -0.06
     draggable
    -0.06
    iš
    -0.06
     breeze
    -0.06
     фрон
    -0.06
    POSITIVE LOGITS
     العربية
    0.06
    ाक
    0.06
    wers
    0.06
    िक
    0.06
    орон
    0.06
    ặp
    0.06
     rival
    0.06
    кт
    0.06
     Nacional
    0.06
    tabl
    0.06
    Act Density 0.001%

    No Known Activations