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

    Neuronpedia

    INDEX
    Explanations

    Text Snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vasion
    -0.26
    å¡ijèĥ¶
    -0.25
     clone
    -0.25
    åīįéĶĭ
    -0.25
     SIG
    -0.24
    èµĶåģ¿
    -0.24
    åıĹ害
    -0.24
    æĺ¥é£İ
    -0.24
     sensitive
    -0.23
    åīį沿
    -0.23
    POSITIVE LOGITS
    anuts
    0.29
    ppelin
    0.28
     heights
    0.28
     myfile
    0.28
     tallest
    0.27
     Heights
    0.27
    Uploaded
    0.26
    æªĹ
    0.26
    èĥ½è¾¾åĪ°
    0.26
    orizontal
    0.26
    Act Density 1.689%

    No Known Activations