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

    Neuronpedia

    INDEX
    Explanations

    Overcoming obstacles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Usuario
    -0.07
     неп
    -0.06
    icamente
    -0.06
    .Flush
    -0.06
     restroom
    -0.06
    �
    -0.06
     khổ
    -0.06
    (left
    -0.06
     Natasha
    -0.06
    며
    -0.06
    POSITIVE LOGITS
     tagName
    0.07
     helf
    0.06
     parliament
    0.06
    :T
    0.06
    روت
    0.06
     меньше
    0.06
    سة
    0.06
    CLUS
    0.06
     }}}
    0.06
    ριν
    0.06
    Act Density 0.036%

    No Known Activations