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

    Neuronpedia

    INDEX
    Explanations

    disease progression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hollywood
    -0.07
    endant
    -0.07
     AM
    -0.07
    endas
    -0.07
    _MIX
    -0.07
    UGE
    -0.06
     clans
    -0.06
    tight
    -0.06
     breeding
    -0.06
    .Point
    -0.06
    POSITIVE LOGITS
    (cs
    0.07
    agger
    0.06
    Favorites
    0.06
         
    0.06
    ropp
    0.06
    getValue
    0.06
     crashed
    0.06
    层
    0.06
    Moh
    0.06
     väl
    0.06
    Act Density 0.030%

    No Known Activations