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

    Neuronpedia

    INDEX
    Explanations

    varied text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cit
    -0.26
    èı²
    -0.25
    èĸľ
    -0.25
    atomy
    -0.25
    .ser
    -0.25
    亲èĩª
    -0.24
    mites
    -0.24
    лик
    -0.24
    plex
    -0.23
    rego
    -0.23
    POSITIVE LOGITS
    åıĪ好
    0.27
    itioner
    0.25
    éĢļåħ³
    0.25
    à¸Ķà¸Ļ
    0.25
    ç½Ĥ
    0.25
    èĤ²
    0.25
     glove
    0.24
    Utf
    0.23
    iche
    0.23
    线索
    0.23
    Act Density 0.043%

    No Known Activations