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

    Neuronpedia

    INDEX
    Explanations

    domains and their contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     និង
    0.53
    지와
    0.52
     and
    0.50
     và
    0.49
     અને
    0.49
     आणि
    0.46
    力和
    0.46
    ແລະ
    0.46
     și
    0.45
    性和
    0.44
    POSITIVE LOGITS
     alike
    0.58
     යන
    0.51
     modes
    0.50
     approaches
    0.50
    といった
    0.48
     એમ
    0.47
     contexts
    0.46
     बाजारों
    0.46
     각각
    0.45
     sectors
    0.44
    Act Density 0.026%

    No Known Activations