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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Filters
    -0.07
     correlations
    -0.07
    larının
    -0.06
    .$$
    -0.06
    ).(
    -0.06
     defenses
    -0.06
     VIC
    -0.06
     communion
    -0.06
    -dess
    -0.06
    ().↵
    -0.06
    POSITIVE LOGITS
    .ct
    0.07
    iesen
    0.06
    平台
    0.06
    zar
    0.06
    :view
    0.06
     Know
    0.06
    ційно
    0.06
    ToolBar
    0.06
    shaw
    0.06
    .Magenta
    0.05
    Act Density 0.115%

    No Known Activations