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

    Neuronpedia

    INDEX
    Explanations

    land area

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    retien
    0.46
     lip
    0.43
     poor
    0.40
     hapless
    0.39
     upl
    0.38
     upland
    0.38
     pesky
    0.38
     problem
    0.37
     vect
    0.37
    常用的
    0.37
    POSITIVE LOGITS
    られた
    0.47
     चुनौतियों
    0.46
    Personendaten
    0.46
     ഞാന്‍
    0.46
     adatt
    0.45
    甚至是
    0.45
     finalised
    0.44
     Παν
    0.44
    Listo
    0.44
     adaptarse
    0.43
    Act Density 0.002%

    No Known Activations