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

    Neuronpedia

    INDEX
    Explanations

    strategic and historic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    1.81
    L
    1.49
    B
    1.48
    S
    1.48
    al
    1.42
    J
    1.40
    U
    1.37
    F
    1.34
     (
    1.34
    T
    1.33
    POSITIVE LOGITS
    ভাবে
    1.01
    ہ
    0.95
    یر
    0.94
    不去
    0.94
    య
    0.94
    সহ
    0.91
    没有
    0.91
    ak
    0.90
     a
    0.89
    ني
    0.89
    Act Density 0.393%

    No Known Activations