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

    Neuronpedia

    INDEX
    Explanations

    author initials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FTER
    -0.07
     ایالات
    -0.07
    fter
    -0.07
    ुत
    -0.06
    ３
    -0.06
     lava
    -0.06
    pecial
    -0.06
    тии
    -0.06
    Feature
    -0.06
    lecture
    -0.06
    POSITIVE LOGITS
     NK
    0.07
    /thumb
    0.06
    WT
    0.06
    午
    0.06
    =YES
    0.06
     atheists
    0.06
     Monterey
    0.06
     stringstream
    0.06
    .isUser
    0.06
    =true
    0.06
    Act Density 0.019%

    No Known Activations