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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deliver
    -0.06
     پي
    -0.06
    ract
    -0.06
    .gstatic
    -0.06
    Unt
    -0.06
     philosopher
    -0.06
     wastewater
    -0.06
     پرد
    -0.06
    	rt
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    \Collections
    0.07
    Scheme
    0.07
     sourcing
    0.07
    MODULE
    0.06
    ahir
    0.06
     설정
    0.06
     George
    0.06
     weekday
    0.06
     railing
    0.06
    UrlParser
    0.06
    Act Density 0.001%

    No Known Activations