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

    Neuronpedia

    INDEX
    Explanations

    crisis support numbers and text lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.74
     Slide
    0.57
     Trump
    0.56
     eres
    0.50
    只
    0.49
     Beaucoup
    0.49
    关联
    0.49
     Frame
    0.48
    Trump
    0.48
     Map
    0.48
    POSITIVE LOGITS
    wool
    0.52
    ίλ
    0.51
    🫤
    0.50
     NFT
    0.49
    Arche
    0.49
    вать
    0.49
    NFT
    0.49
    ИН
    0.49
     ஒன்றிய
    0.49
    Ukrainian
    0.48
    Act Density 0.108%

    No Known Activations