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

    Neuronpedia

    INDEX
    Explanations

    project references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있을
    -0.08
    	cont
    -0.07
     stares
    -0.07
     שני
    -0.07
    界的
    -0.07
    肱
    -0.07
    	step
    -0.06
    -0.06
     siècle
    -0.06
    之争
    -0.06
    POSITIVE LOGITS
     executable
    0.07
    ([{
    0.07
    (proc
    0.07
     lively
    0.07
    Seconds
    0.06
    运河
    0.06
     mobil
    0.06
     notification
    0.06
     essay
    0.06
    تنسيق
    0.06
    Act Density 0.003%

    No Known Activations