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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bran
    -0.08
     disple
    -0.07
    egrator
    -0.07
     Henry
    -0.07
    интерес
    -0.07
    早期
    -0.07
    警察
    -0.07
    -angle
    -0.07
    -social
    -0.07
    ༄
    -0.06
    POSITIVE LOGITS
    ANCH
    0.07
    agic
    0.07
     LOSS
    0.07
    .viewmodel
    0.07
    问我
    0.06
    谜
    0.06
     typed
    0.06
     alt
    0.06
    CellStyle
    0.06
    inished
    0.06
    Act Density 0.006%

    No Known Activations