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

    Neuronpedia

    INDEX
    Explanations

    Love is respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.83
    an
    1.64
    ively
    1.57
    т
    1.54
    ת
    1.48
    ي
    1.46
    ان
    1.42
     хотела
    1.40
    i
    1.37
    rà
    1.36
    POSITIVE LOGITS
     perj
    1.69
    ̣c
    1.56
     dengue
    1.54
     pepe
    1.49
     monotonically
    1.49
     injective
    1.49
     cardiomy
    1.49
     prokary
    1.48
     poils
    1.47
    ಂಗ್
    1.47
    Act Density 0.002%

    No Known Activations