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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    执
    -0.06
     nanop
    -0.06
     mech
    -0.06
     tác
    -0.06
     Hiro
    -0.06
    "F
    -0.06
     yerine
    -0.06
    _dual
    -0.06
     Member
    -0.06
     Bust
    -0.06
    POSITIVE LOGITS
     edilir
    0.08
    /path
    0.07
     Santa
    0.06
    انت
    0.06
    olina
    0.06
    距离
    0.06
    nict
    0.06
    θεν
    0.06
    /plain
    0.06
    nesia
    0.06
    Act Density 0.001%

    No Known Activations