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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æľµ
    -0.29
    éĺ»åĬĽ
    -0.28
    mát
    -0.27
    æķĮ人
    -0.26
    è®°å¿Ĩ
    -0.26
    nerg
    -0.25
    åıĭ好
    -0.25
     oppos
    -0.25
     sourceMappingURL
    -0.25
    å¥ĩ
    -0.25
    POSITIVE LOGITS
    ialog
    0.27
    ovel
    0.25
    overs
    0.25
    illos
    0.25
    eve
    0.24
     dif
    0.24
     disg
    0.23
    ece
    0.23
    ä¸Ģ身
    0.23
     lanc
    0.23
    Act Density 0.025%

    No Known Activations