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

    Neuronpedia

    INDEX
    Explanations

    dimension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⵍ
    -0.07
    >Delete
    -0.06
     Independ
    -0.06
     feet
    -0.06
    บน
    -0.06
    ağını
    -0.06
     hopeful
    -0.06
    錯誤
    -0.06
    _Data
    -0.06
    筹
    -0.06
    POSITIVE LOGITS
    [action
    0.08
    .emit
    0.08
    (alias
    0.08
    骤
    0.07
     instantiate
    0.07
    -spacing
    0.07
    Deque
    0.07
    ewitness
    0.07
     evento
    0.07
    класс
    0.07
    Act Density 0.053%

    No Known Activations