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

    Neuronpedia

    INDEX
    Explanations

    question words and terminal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Median
    0.45
    le
    0.45
     Jerez
    0.44
    ancipation
    0.43
     at
    0.43
     such
    0.42
    ounce
    0.42
     받는
    0.42
     Jacobian
    0.42
    Dimensional
    0.41
    POSITIVE LOGITS
    НИ
    0.50
     froide
    0.49
     показали
    0.47
     patria
    0.47
     funcione
    0.46
    ニング
    0.46
     publiés
    0.46
    安卓
    0.45
     isolé
    0.45
    <unused56>
    0.44
    Act Density 0.001%

    No Known Activations