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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اشت
    -0.07
     Second
    -0.07
    lations
    -0.07
    360
    -0.07
    _SE
    -0.07
    qualification
    -0.06
    prefix
    -0.06
    Exceptions
    -0.06
    руш
    -0.06
    ikt
    -0.06
    POSITIVE LOGITS
     reimb
    0.07
     даль
    0.06
    ็กชาย
    0.06
     расход
    0.06
     responsive
    0.06
     Báo
    0.06
     подаль
    0.06
    ік
    0.06
     fined
    0.06
     Орг
    0.06
    Act Density 0.012%

    No Known Activations