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

    Neuronpedia

    INDEX
    Explanations

    thinness and slenderness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    越多
    0.42
     सुरक्षित
    0.40
    甕
    0.40
    FORMAN
    0.38
     bruto
    0.37
    囵
    0.36
     久
    0.36
     LUMP
    0.36
    宏
    0.36
    িকর
    0.36
    POSITIVE LOGITS
     thin
    4.34
     Thin
    3.92
    Thin
    3.91
    thin
    3.72
     thinner
    3.55
    薄
    3.52
     薄
    2.91
     thinning
    2.89
     slim
    2.78
    얇
    2.73
    Act Density 0.106%

    No Known Activations