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

    Neuronpedia

    INDEX
    Explanations

    code explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nějak
    0.90
     Epidemi
    0.85
     rzeczyw
    0.83
    が好き
    0.81
    实在是
    0.80
     bisschen
    0.80
     sebenarnya
    0.79
     leider
    0.79
     susah
    0.78
     buurt
    0.78
    POSITIVE LOGITS
     resulting
    1.67
     developed
    1.60
     resultant
    1.58
     proposed
    1.55
    resulting
    1.49
     devised
    1.46
     created
    1.43
     invented
    1.40
    developed
    1.39
     obtained
    1.39
    Act Density 0.241%

    No Known Activations