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

    Neuronpedia

    INDEX
    Explanations

    advanced complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recibió
    0.73
     миллиар
    0.72
     согласно
    0.70
    AAAAAAAAAAAAAAAA
    0.69
     uniforme
    0.69
    benzene
    0.69
    㕷
    0.66
     संतुलित
    0.66
     berwarna
    0.66
    getDefaultSh
    0.65
    POSITIVE LOGITS
     complexity
    2.07
     complicated
    1.84
     hassle
    1.82
     complexities
    1.82
     inconvenience
    1.82
    Complexity
    1.74
    complexity
    1.73
     Complexity
    1.71
     tedious
    1.71
    手間
    1.68
    Act Density 0.683%

    No Known Activations