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

    Neuronpedia

    INDEX
    Explanations

    URLs following informational content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shimmering
    0.29
     grassy
    0.28
     grass
    0.27
    item
    0.26
     넓
    0.26
     pavement
    0.25
    หล
    0.25
    colored
    0.25
    grass
    0.25
     grains
    0.25
    POSITIVE LOGITS
     affirme
    0.32
    فرض
    0.28
    ට්
    0.28
     comportamenti
    0.27
    চারের
    0.27
     postdoc
    0.27
     championed
    0.26
    傕
    0.26
     جوړونک
    0.26
    pkins
    0.26
    Act Density 0.000%

    No Known Activations