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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yards
    -0.25
    æľīè¿ĩ
    -0.25
    birthdate
    -0.24
    æĺ¯æľī
    -0.24
    Front
    -0.24
    Discover
    -0.23
    .blob
    -0.23
    ãģĸ
    -0.23
    CG
    -0.22
    ä¸įçŁ¥
    -0.22
    POSITIVE LOGITS
    gether
    0.31
    orpor
    0.27
    autiful
    0.27
    imensional
    0.26
    ftware
    0.26
    itecture
    0.26
    lications
    0.25
    aight
    0.24
    itionally
    0.23
    uron
    0.23
    Act Density 0.382%

    No Known Activations