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

    Neuronpedia

    INDEX
    Explanations

    reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    推荐
    -0.06
    čen
    -0.06
     LJ
    -0.06
     فاصله
    -0.06
     Совет
    -0.06
    _inline
    -0.06
     Allowed
    -0.06
    .fade
    -0.06
    เห
    -0.06
    ол
    -0.06
    POSITIVE LOGITS
     таблет
    0.06
    .Sin
    0.06
    strate
    0.06
    emics
    0.06
     ř
    0.06
    flamm
    0.06
     disob
    0.06
     プロ
    0.06
    Mbps
    0.06
    見
    0.06
    Act Density 0.007%

    No Known Activations