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

    Neuronpedia

    INDEX
    Explanations

    state or starting point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seterusnya
    0.42
    ":
    0.38
     sometime
    0.38
     fatigued
    0.38
    将来
    0.37
    体内
    0.35
     inboard
    0.35
     الداخل
    0.35
     texId
    0.35
     dissu
    0.34
    POSITIVE LOGITS
     главной
    0.41
    ethi
    0.38
    рного
    0.38
     Vincent
    0.38
    ="%
    0.38
     लू
    0.37
     館
    0.37
     Gentile
    0.37
    circledR
    0.36
     行っ
    0.36
    Act Density 0.000%

    No Known Activations