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

    Neuronpedia

    INDEX
    Explanations

    actual measurement or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سالب
    0.45
     финансо
    0.41
     posthum
    0.39
     sağlık
    0.37
     kvůli
    0.36
     (!)
    0.35
     wyłącznie
    0.35
     Duits
    0.35
    对自己
    0.34
    一个人
    0.34
    POSITIVE LOGITS
     each
    0.46
    ম
    0.46
     sicuramente
    0.45
    this
    0.45
    म
    0.44
    ㅈ
    0.43
     formations
    0.43
    それぞれの
    0.42
    m
    0.42
    এই
    0.42
    Act Density 0.002%

    No Known Activations