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

    Neuronpedia

    INDEX
    Explanations

    comparing options and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     záz
    0.51
    濬
    0.48
    楠
    0.47
    Magn
    0.46
     árboles
    0.46
     drinks
    0.44
    汨
    0.44
     skyl
    0.42
     roca
    0.42
    岩
    0.41
    POSITIVE LOGITS
    eth
    0.50
    ž
    0.48
    udere
    0.47
    ancies
    0.47
    のですが
    0.46
    olve
    0.46
    antiate
    0.45
    ach
    0.45
    apan
    0.45
    urpose
    0.45
    Act Density 0.015%

    No Known Activations