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

    Neuronpedia

    INDEX
    Explanations

    collaborative storytelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Editions
    0.39
     Sol
    0.38
     towns
    0.37
    觎
    0.37
     cidades
    0.36
     ciudades
    0.36
     villes
    0.36
     X
    0.35
     conclusion
    0.35
    quela
    0.35
    POSITIVE LOGITS
     กําลัง
    0.42
    🤺
    0.41
     सदस्य
    0.40
     feedstock
    0.40
    новниш
    0.39
    Especially
    0.39
    Aaj
    0.38
     Guil
    0.38
     необходимых
    0.38
     incubating
    0.38
    Act Density 0.000%

    No Known Activations