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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    常德
    -0.27
     Administration
    -0.25
    èĥĮ
    -0.24
    æĮŀ
    -0.24
    others
    -0.24
    /Admin
    -0.24
    otto
    -0.24
    isia
    -0.23
     Others
    -0.23
    æĢĢ
    -0.23
    POSITIVE LOGITS
    stance
    0.29
    urement
    0.28
    æĹ¥æĬ¥éģĵ
    0.27
     anonymously
    0.26
    przed
    0.26
    æ·±å¤ľ
    0.25
    opot
    0.25
    åīįåįģ
    0.24
    pread
    0.24
    umer
    0.24
    Act Density 0.025%

    No Known Activations