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

    Neuronpedia

    INDEX
    Explanations

    start of Spanish phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.85
     …
    0.84
    <0xC2>
    0.84
    ,.
    0.84
      
    0.83
    0.83
    …
    0.83
     […]
    0.83
    ...
    0.81
     ​​
    0.80
    POSITIVE LOGITS
     pediatrician
    0.79
    皞
    0.78
    <unused96>
    0.77
    >∕</
    0.74
    <unused25>
    0.74
    嵓
    0.74
    Ꮘ
    0.73
     Iphone
    0.73
    兒子
    0.73
    pisah
    0.72
    Act Density 0.185%

    No Known Activations