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

    Neuronpedia

    INDEX
    Explanations

    component setup keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aworld
    0.80
    澧
    0.78
    squared
    0.74
     Chapel
    0.74
    渍
    0.74
     красо
    0.73
     экране
    0.73
     TGF
    0.73
    ukka
    0.73
     Kisi
    0.72
    POSITIVE LOGITS
     JavaBeans
    0.71
    ໄ
    0.70
    0.69
    ടിയ
    0.69
     injection
    0.68
    독
    0.67
    Prop
    0.67
     hem
    0.65
    谷
    0.64
     HTML
    0.63
    Act Density 0.024%

    No Known Activations