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

    Neuronpedia

    INDEX
    Explanations

    EC50 values in experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )$_
    -0.07
     forever
    -0.07
     Example
    -0.07
     Gun
    -0.07
    Channel
    -0.07
     cán
    -0.07
     кон
    -0.07
    查
    -0.07
    __)↵
    -0.07
    _submit
    -0.07
    POSITIVE LOGITS
    PKG
    0.07
    琥
    0.07
    碉
    0.07
    밑
    0.07
    算了
    0.07
     livelihood
    0.07
     manuals
    0.06
     WhatsApp
    0.06
     owed
    0.06
     Lage
    0.06
    Act Density 0.063%

    No Known Activations