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

    Neuronpedia

    INDEX
    Explanations

    Scientific terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    speaker
    -0.07
    `)↵
    -0.07
    rap
    -0.07
    .active
    -0.07
    ));↵
    -0.07
    `);↵
    -0.07
    ')↵
    -0.06
    ↵
    -0.06
    이에
    -0.06
    ()
↵
    -0.06
    POSITIVE LOGITS
     حض
    0.07
     δο
    0.07
     ifs
    0.07
     bs
    0.06
     DateFormat
    0.06
     doctr
    0.06
     KS
    0.06
    ớ
    0.06
    	NS
    0.06
     mAuth
    0.06
    Act Density 0.297%

    No Known Activations