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

    Neuronpedia

    INDEX
    Explanations

    plural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mirrors
    -0.07
    iliki
    -0.07
     West
    -0.07
    *d
    -0.07
     years
    -0.07
     Seas
    -0.06
    compass
    -0.06
    idential
    -0.06
    .Out
    -0.06
     judiciary
    -0.06
    POSITIVE LOGITS
    'LBL
    0.07
     ⓘ
    0.06
     数
    0.06
     verge
    0.06
    addTo
    0.06
     getir
    0.06
    <=$
    0.06
    _mE
    0.06
    .mContext
    0.06
     tracing
    0.06
    Act Density 0.002%

    No Known Activations