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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ши
    -0.06
     Đài
    -0.06
    \Foundation
    -0.06
     Cao
    -0.06
     gent
    -0.06
    ")+
    -0.06
    ("")
    -0.06
     corresponds
    -0.06
    mites
    -0.06
     establishments
    -0.06
    POSITIVE LOGITS
    -bit
    0.07
    ाएग
    0.07
    .Admin
    0.07
     Fantasy
    0.06
    _Move
    0.06
    -hour
    0.06
     金
    0.06
    imat
    0.06
    ultip
    0.06
    _UI
    0.06
    Act Density 0.640%

    No Known Activations