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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron is detecting HTML (or XML) markup tags (i.e. text enclosed in “<…>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kis
    -0.06
    361
    -0.06
    .Image
    -0.06
    wt
    -0.06
    .Client
    -0.06
     Comcast
    -0.06
    ülebilir
    -0.06
    〇
    -0.05
    Miami
    -0.05
    marsh
    -0.05
    POSITIVE LOGITS
    놓
    0.07
     barrels
    0.07
    .JOptionPane
    0.07
     mohla
    0.07
    окрем
    0.07
    -END
    0.07
    .PERMISSION
    0.07
    _top
    0.06
     입
    0.06
    (ps
    0.06
    Act Density 0.004%

    No Known Activations