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

    Neuronpedia

    INDEX
    Explanations

    crisis support lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Immediately
    0.74
     কয়েকটি
    0.71
    ത്തോടെ
    0.68
    Stability
    0.67
    आप
    0.67
    More
    0.66
    Various
    0.65
     हिस्सा
    0.64
    Sam
    0.64
     तंत्र
    0.64
    POSITIVE LOGITS
    博物館
    0.96
    ҝ
    0.94
    etil
    0.93
    Hd
    0.93
     kostet
    0.90
    ंदरे
    0.90
    createSprite
    0.88
    elcome
    0.88
    csim
    0.88
    etl
    0.88
    Act Density 0.021%

    No Known Activations