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

    Neuronpedia

    INDEX
    Explanations

    asking "what"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     осмо
    0.40
    sh
    0.39
    ark
    0.38
    কিং
    0.38
    Penis
    0.38
    un
    0.38
     CHILD
    0.38
    ugh
    0.37
    ថ្ង
    0.37
    SIDE
    0.37
    POSITIVE LOGITS
    보다
    0.50
     beiden
    0.50
    Both
    0.48
    มีความ
    0.46
    両
    0.46
     beide
    0.46
     both
    0.45
     दोनों
    0.43
     keduanya
    0.42
    ണ്
    0.42
    Act Density 0.000%

    No Known Activations