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

    Neuronpedia

    INDEX
    Explanations

    algorithms and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $\
    0.41
    平和
    0.37
    itating
    0.37
    ucceed
    0.36
    ซิต
    0.36
     $\}$
    0.35
    حی
    0.35
     ')
    0.34
     Soy
    0.34
    rike
    0.34
    POSITIVE LOGITS
     algorithm
    0.68
    algorithm
    0.68
     algorit
    0.63
     Algorithms
    0.61
     algorithmic
    0.61
    Algorithm
    0.61
     Alg
    0.59
    Algorithms
    0.59
    algorithms
    0.59
     alg
    0.58
    Act Density 0.000%

    No Known Activations