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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    4
    -0.07
    Ы
    -0.07
     supporting
    -0.06
    3
    -0.06
    ẫu
    -0.06
     complaints
    -0.06
    2
    -0.06
     ultimo
    -0.06
     sitcom
    -0.06
    binding
    -0.06
    POSITIVE LOGITS
    .int
    0.07
    :!
    0.06
     ffi
    0.06
    .tools
    0.06
    _quick
    0.06
    MDB
    0.06
    DISABLE
    0.06
     ECB
    0.06
     CSR
    0.06
     united
    0.06
    Act Density 0.039%

    No Known Activations