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

    Neuronpedia

    INDEX
    Explanations

    figure references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tanning
    -0.09
     fierce
    -0.09
     nightclub
    -0.08
    หมด
    -0.08
     tones
    -0.08
     wilderness
    -0.08
    �
    -0.08
     gambling
    -0.08
    兼职
    -0.08
     grocery
    -0.08
    POSITIVE LOGITS
     Appendix
    0.12
     рисун
    0.12
     Figure
    0.12
     numbering
    0.12
    编号
    0.11
    Figure
    0.11
     numbered
    0.11
     Fig
    0.11
     referenced
    0.10
     Figures
    0.10
    Act Density 0.014%

    No Known Activations