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

    Neuronpedia

    INDEX
    Explanations

    Negative topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("(
    -0.07
     GX
    -0.07
     همیشه
    -0.06
     moderated
    -0.06
     Theatre
    -0.06
    aph
    -0.06
    层
    -0.06
     mund
    -0.06
    ENTRY
    -0.06
    -holder
    -0.06
    POSITIVE LOGITS
    	description
    0.06
     Iranian
    0.06
     dentist
    0.06
    ropping
    0.06
    ibe
    0.06
    ida
    0.06
    Inserted
    0.06
     mở
    0.06
    Dan
    0.06
     emergence
    0.06
    Act Density 0.000%

    No Known Activations