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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     класс
    -0.06
     Huyện
    -0.06
     통해
    -0.06
     �
    -0.06
    もっと
    -0.06
    .shapes
    -0.06
     خر
    -0.06
    .mkdir
    -0.06
     Travis
    -0.06
     nihil
    -0.06
    POSITIVE LOGITS
     stacking
    0.07
    ADA
    0.07
     CPI
    0.07
     sideline
    0.06
     alignment
    0.06
    �프
    0.06
     staging
    0.06
    BSD
    0.06
    αλύτε
    0.06
     total
    0.06
    Act Density 0.025%

    No Known Activations