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

    Neuronpedia

    INDEX
    Explanations

    and even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?:
    0.92
    :
    0.89
    ':
    0.85
    ":
    0.82
    :",
    0.80
     :
    0.79
    :**
    0.78
     =
    0.73
    =
    0.73
    this
    0.72
    POSITIVE LOGITS
     even
    2.44
     bahkan
    2.18
     даже
    2.15
     навіть
    2.04
     sogar
    1.97
    甚至是
    1.94
    甚至
    1.90
     zelfs
    1.89
     thậm
    1.86
     এমনকি
    1.85
    Act Density 0.813%

    No Known Activations