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

    Neuronpedia

    INDEX
    Explanations

    appear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sunglasses
    0.34
     brazos
    0.33
     an
    0.32
    -
    0.32
     번째
    0.31
    টি
    0.31
    種類の
    0.31
     buttermilk
    0.30
     lipoproteins
    0.30
     a
    0.30
    POSITIVE LOGITS
    ባቸው
    0.37
    ுகளை
    0.36
     על
    0.35
    riving
    0.33
    0.33
     முன்
    0.33
    rive
    0.33
     മുതല്‍
    0.33
    โดย
    0.33
     concernant
    0.33
    Act Density 0.043%

    No Known Activations