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

    Neuronpedia

    INDEX
    Explanations

    grammatically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ுகிறார்கள்
    0.86
    Hundreds
    0.82
    Alternatives
    0.80
     Minder
    0.78
    ailure
    0.77
     viti
    0.75
    atasi
    0.72
    Yea
    0.71
     commerciaux
    0.70
    <unused2172>
    0.70
    POSITIVE LOGITS
    ث
    0.74
    وفي
    0.72
     zom
    0.71
     ولك
    0.71
    আরো
    0.70
     Student
    0.70
    houses
    0.70
     aproveitar
    0.69
     jeweils
    0.69
     জন্যও
    0.68
    Act Density 0.001%

    No Known Activations