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

    Neuronpedia

    INDEX
    Explanations

    rödinger, Fenugreek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.57
     is
    0.54
     are
    0.50
     has
    0.50
     in
    0.47
     or
    0.47
    ্ট
    0.47
    is
    0.46
     cameos
    0.46
     laurels
    0.43
    POSITIVE LOGITS
    2
    0.54
    ’
    0.53
    Une
    0.53
    1
    0.53
    évolution
    0.50
    etzung
    0.47
    Antoine
    0.46
    Sans
    0.46
    FULLY
    0.45
    ڦ
    0.45
    Act Density 0.002%

    No Known Activations