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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﮮ
    -0.07
    év
    -0.07
     consulted
    -0.07
    .tf
    -0.06
    监狱
    -0.06
    Comb
    -0.06
    _Speed
    -0.06
    转移到
    -0.06
    非常明显
    -0.06
    bar
    -0.06
    POSITIVE LOGITS
    0.07
    	order
    0.07
    _REFRESH
    0.07
    异议
    0.07
    古い
    0.07
     jokes
    0.07
    	WHERE
    0.07
     treat
    0.07
     ===
    0.06
     disparate
    0.06
    Act Density 0.010%

    No Known Activations