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
     Said
    -0.07
    лению
    -0.07
     Diğer
    -0.07
     acciones
    -0.07
    евид
    -0.07
    .just
    -0.06
    드립니다
    -0.06
    zion
    -0.06
     helicopt
    -0.06
     Pace
    -0.06
    POSITIVE LOGITS
     psychological
    0.06
    τζ
    0.06
     Designer
    0.06
    ,E
    0.06
    igy
    0.06
     rum
    0.06
     leads
    0.06
    ',{
    0.06
     Lead
    0.06
     NC
    0.06
    Act Density 0.034%

    No Known Activations