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
     образования
    -0.07
    once
    -0.07
    esar
    -0.07
    ศ
    -0.07
    _observer
    -0.07
     Colonel
    -0.07
    _nombre
    -0.06
    _error
    -0.06
     stamina
    -0.06
    še
    -0.06
    POSITIVE LOGITS
     APPLICATION
    0.07
    Tick
    0.06
     restraining
    0.06
    .fixed
    0.06
    recipient
    0.06
    Subviews
    0.06
    :@"%@",
    0.06
    帽
    0.06
     supported
    0.06
     frogs
    0.06
    Act Density 0.017%

    No Known Activations