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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icken
    -0.08
    Pick
    -0.07
     Ор
    -0.07
     DOJ
    -0.07
    ill
    -0.07
    ILL
    -0.07
    .pick
    -0.07
     startPosition
    -0.07
    make
    -0.07
     Harding
    -0.07
    POSITIVE LOGITS
    =\"
    0.08
    .
    0.07
     transcript
    0.07
    趣
    0.07
     surrogate
    0.07
     queryInterface
    0.07
     Lives
    0.06
    .NoArgsConstructor
    0.06
    \")
    0.06
     cuộc
    0.06
    Act Density 0.018%

    No Known Activations