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

    Neuronpedia

    INDEX
    Explanations

    reporting past data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    康复
    -0.08
    ﴀ
    -0.07
    '],
    -0.07
     porcelain
    -0.07
     replicate
    -0.07
     eps
    -0.07
    🐺
    -0.07
    钢琴
    -0.07
     allocated
    -0.07
     scanner
    -0.06
    POSITIVE LOGITS
    Appe
    0.07
    mana
    0.06
     Ning
    0.06
    /start
    0.06
     Ar
    0.06
    _votes
    0.06
    enery
    0.06
    ibre
    0.06
     Garrison
    0.06
    EI
    0.06
    Act Density 0.022%

    No Known Activations