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

    Neuronpedia

    INDEX
    Explanations

    sept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -intensive
    -0.07
     mafia
    -0.07
     automobile
    -0.06
     involves
    -0.06
    _CTX
    -0.06
    Life
    -0.06
     mie
    -0.06
    "D
    -0.06
    Lu
    -0.06
    Disallow
    -0.06
    POSITIVE LOGITS
     cessation
    0.07
     βο
    0.06
     Roberto
    0.06
     베스트
    0.06
     BIG
    0.06
     Saga
    0.06
    (valid
    0.06
    ικών
    0.06
     янва
    0.06
     �
    0.06
    Act Density 0.002%

    No Known Activations