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

    Neuronpedia

    INDEX
    Explanations

    how to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cut
    -0.07
    𝐡
    -0.07
    죤
    -0.07
     cri
    -0.07
    ㉥
    -0.07
    兰州
    -0.06
    图书
    -0.06
     Dancing
    -0.06
    _stuff
    -0.06
    _patch
    -0.06
    POSITIVE LOGITS
    .name
    0.07
    été
    0.07
    带来
    0.06
    .where
    0.06
    back
    0.06
    amaha
    0.06
     mis
    0.06
    \Factory
    0.06
    팔
    0.06
     глаз
    0.06
    Act Density 0.247%

    No Known Activations