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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    看的
    -0.09
     olmayan
    -0.08
     pioneered
    -0.08
    Slices
    -0.08
    发展的
    -0.08
     dying
    -0.08
    工作的
    -0.08
    -0.08
     BNP
    -0.07
    -0.07
    POSITIVE LOGITS
    ῦ
    0.09
    ✓
    0.08
    ☆☆
    0.08
    boxed
    0.08
    �
    0.08
    ▲
    0.08
    ×
    0.08
    @\
    0.08
     obstacle
    0.07
    ✔
    0.07
    Act Density 0.026%
    No Known Activations