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

    Neuronpedia

    INDEX
    Explanations

    convolutional neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dataSize
    -0.07
    _ep
    -0.07
     Supports
    -0.06
    flater
    -0.06
     Merge
    -0.06
    licer
    -0.06
    质
    -0.06
    interpreter
    -0.06
    ORMAL
    -0.06
     из
    -0.06
    POSITIVE LOGITS
    rias
    0.07
    umas
    0.06
     implicated
    0.06
     them
    0.06
    clr
    0.06
    erner
    0.06
     перепис
    0.06
    .alert
    0.06
    etrain
    0.06
    vf
    0.06
    Act Density 0.006%

    No Known Activations