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

    Neuronpedia

    INDEX
    Explanations

    compelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Luigi
    -0.07
     tank
    -0.07
    bero
    -0.07
     totaled
    -0.07
    йте
    -0.07
    incident
    -0.07
    ㅄ
    -0.06
     Juni
    -0.06
     준
    -0.06
    Nb
    -0.06
    POSITIVE LOGITS
     compelling
    0.08
    作为一种
    0.07
     immutable
    0.07
    剁
    0.07
    梨
    0.07
    目的地
    0.06
     `'
    0.06
    .grpc
    0.06
     stringWith
    0.06
    香味
    0.06
    Act Density 0.004%

    No Known Activations