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

    Neuronpedia

    INDEX
    Explanations

    references to algorithms and algorithm-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    algorithm references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })`
    -0.40
     kekasih
    -0.40
     sementara
    -0.40
     alltså
    -0.40
     tartalomajánló
    -0.39
     vandens
    -0.39
     kurie
    -0.39
     seksual
    -0.38
     SEDS
    -0.38
     negru
    -0.38
    POSITIVE LOGITS
    Algorithm
    2.23
     Algorithm
    1.91
    algorithm
    1.69
     algorithm
    1.62
    GORITHM
    1.36
     algoritmo
    1.31
    Algo
    1.26
    algo
    1.23
    算法
    1.23
    Alg
    1.21
    Act Density 0.011%

    No Known Activations