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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    岁以上
    -0.08
    lemetry
    -0.08
    iley
    -0.07
    很高的
    -0.07
    opolitan
    -0.07
    太子
    -0.07
     Lok
    -0.07
    参观
    -0.07
     necklace
    -0.07
    ordin
    -0.07
    POSITIVE LOGITS
     Lab
    0.07
     bounds
    0.07
    ⫸
    0.07
     forces
    0.06
    ;'↵
    0.06
    set
    0.06
     окол
    0.06
    within
    0.06
     comentarios
    0.06
     β
    0.06
    Act Density 0.014%

    No Known Activations