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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narrowed
    -0.07
     Lever
    -0.07
    ури
    -0.06
    .Pre
    -0.06
    (Const
    -0.06
     autom
    -0.06
    oma
    -0.06
     entrepreneurial
    -0.06
     hb
    -0.06
    .Ar
    -0.06
    POSITIVE LOGITS
     отдель
    0.06
    _positive
    0.06
    علق
    0.06
    udy
    0.06
    .Utilities
    0.06
    電子
    0.06
     Overview
    0.06
    /manual
    0.06
    DEST
    0.06
     Legends
    0.06
    Act Density 0.296%

    No Known Activations