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

    Neuronpedia

    INDEX
    Explanations

    sophisticated algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    captivity
    0.82
     narr
    0.77
     déliv
    0.75
    レッスン
    0.75
     freedoms
    0.73
     freestanding
    0.73
     willingly
    0.71
     desayuno
    0.70
    loggedin
    0.70
    coach
    0.70
    POSITIVE LOGITS
     algorithms
    2.48
     algorithm
    2.46
     Algorithm
    2.35
    算法
    2.32
     Algorithms
    2.26
     алгорит
    2.22
     algoritmo
    2.19
    Algorithm
    2.18
     algorit
    2.17
    algorithm
    2.14
    Act Density 1.289%

    No Known Activations