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

    Neuronpedia

    INDEX
    Explanations

    cluster names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .??.??"]
    0.29
    BlockUsed
    0.28
     Heterocycl
    0.28
    ismatch
    0.27
    꼫
    0.27
     -----------
    0.26
    ratulations
    0.26
    allenges
    0.26
    ையை
    0.26
     Поэтому
    0.26
    POSITIVE LOGITS
    T
    0.33
    。
    0.29
    ла
    0.28
     K
    0.28
     T
    0.28
    D
    0.27
    ，
    0.26
    ві
    0.26
     F
    0.26
    S
    0.25
    Act Density 0.091%

    No Known Activations