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

    Neuronpedia

    INDEX
    Explanations

    latex commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நூற்றாண்டில்
    0.66
    路撒
    0.62
     significativa
    0.58
     carriera
    0.57
     fenómenos
    0.56
    욌
    0.56
     கலங்கரை
    0.55
     Carre
    0.55
    𝑬
    0.55
     seashore
    0.55
    POSITIVE LOGITS
     Condo
    0.61
     ,
    0.60
    ila
    0.57
     Office
    0.56
    هُ
    0.55
    MS
    0.55
    ใน
    0.54
    ild
    0.54
    Office
    0.53
    Hospital
    0.53
    Act Density 0.003%

    No Known Activations