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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rollo
    -0.27
     luc
    -0.27
    çµIJæĿŁ
    -0.25
    æĿª
    -0.25
    loat
    -0.25
    çĽijçĿ£æ£ĢæŁ¥
    -0.24
    ä¼į
    -0.24
    peg
    -0.24
     rolling
    -0.24
    olor
    -0.23
    POSITIVE LOGITS
    å¼Ĥ
    0.29
    eden
    0.28
    rone
    0.27
     borrowed
    0.27
    æİī
    0.26
    åijĬè¯ī她
    0.26
     heter
    0.26
    失
    0.25
    Kr
    0.25
    åı³
    0.24
    Act Density 0.002%

    No Known Activations