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

    Neuronpedia

    INDEX
    Explanations

    project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Noticed
    -0.07
    erin
    -0.06
    .Member
    -0.06
     weighed
    -0.06
    _SAMPLE
    -0.06
    _PEER
    -0.06
    663
    -0.06
    869
    -0.06
     بسی
    -0.06
     kiss
    -0.06
    POSITIVE LOGITS
     nez
    0.08
     už
    0.07
     Aç
    0.07
    -router
    0.07
     Group
    0.07
    ız
    0.07
     varsa
    0.07
    (function
    0.07
     Node
    0.07
     problème
    0.07
    Act Density 0.003%

    No Known Activations