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

    Neuronpedia

    INDEX
    Explanations

    image transparency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pool
    -0.07
    Dump
    -0.07
     Hours
    -0.07
     địa
    -0.07
    ->{
    -0.07
    _plus
    -0.07
    Alert
    -0.06
     UIL
    -0.06
    (suite
    -0.06
    Test
    -0.06
    POSITIVE LOGITS
     Backpack
    0.07
    مد
    0.07
     Caption
    0.06
    řed
    0.06
     underestimated
    0.06
    Textbox
    0.06
    平台
    0.05
    icture
    0.05
     competed
    0.05
    ulling
    0.05
    Act Density 0.009%

    No Known Activations