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

    Neuronpedia

    INDEX
    Explanations

    mention, refer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zimmerman
    -0.07
     Joseph
    -0.07
     paddle
    -0.07
     ofere
    -0.07
    amic
    -0.07
    ukai
    -0.07
     usable
    -0.07
     Turbo
    -0.07
     filosofía
    -0.07
     microw
    -0.07
    POSITIVE LOGITS
    引用
    0.09
     пове
    0.08
    არ
    0.08
     attribut
    0.08
    Referenced
    0.08
    ಐ
    0.08
    指出
    0.08
    ennent
    0.08
     сюжет
    0.08
     있어
    0.08
    Act Density 0.025%

    No Known Activations