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

    Neuronpedia

    INDEX
    Explanations

    Code queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (metric
    -0.07
    立刻
    -0.07
    .Description
    -0.07
     ships
    -0.07
    處
    -0.07
    ags
    -0.06
    Tabla
    -0.06
     VAN
    -0.06
     Prayer
    -0.06
    其实
    -0.06
    POSITIVE LOGITS
    .getD
    0.07
    xFFF
    0.07
    .addRow
    0.06
     kostenlose
    0.06
     neod
    0.06
    .APPLICATION
    0.06
     آسی
    0.06
    .roll
    0.06
    cky
    0.06
     Beta
    0.06
    Act Density 0.116%

    No Known Activations