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

    Neuronpedia

    INDEX
    Explanations

    <|start|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thunderstorms
    -0.09
     fizik
    -0.08
    орач
    -0.08
    Adaptor
    -0.08
     обеспечить
    -0.08
     físicos
    -0.08
    ਾਹ
    -0.07
     Rau
    -0.07
    �
    -0.07
     Physical
    -0.07
    POSITIVE LOGITS
     consequential
    0.09
     subsequent
    0.08
     biblical
    0.08
    Bib
    0.08
     bate
    0.08
    сиа
    0.08
    ----↵↵
    0.08
    ("---
    0.07
    ボ
    0.07
     daneben
    0.07
    Act Density 0.003%

    No Known Activations