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

    Neuronpedia

    INDEX
    Explanations

    story names

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     stmt
    -0.08
     vals
    -0.07
    #SBATCH
    -0.07
     ../../../
    -0.07
    .nc
    -0.07
    世纪
    -0.07
     thought
    -0.07
     `,
    -0.07
    锨
    -0.07
     %%
    -0.07
    POSITIVE LOGITS
    �
    0.07
    successful
    0.06
    滑雪
    0.06
    늄
    0.06
    尽情
    0.06
    买到
    0.06
     Mobility
    0.06
    เสน
    0.06
    Ϝ
    0.06
    솥
    0.06
    Act Density 0.047%

    No Known Activations