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

    Neuronpedia

    INDEX
    Explanations

    Lake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pruitt
    -0.07
    .spotify
    -0.07
     Emit
    -0.07
     Brett
    -0.07
     Morrison
    -0.06
    'im
    -0.06
    gorithms
    -0.06
     pořad
    -0.06
    须
    -0.06
     resentment
    -0.06
    POSITIVE LOGITS
     Lake
    0.24
     lake
    0.20
    Lake
    0.19
     Lakes
    0.16
     lakes
    0.14
    lake
    0.10
    KE
    0.09
    AKE
    0.09
    ake
    0.08
     Lakers
    0.08
    Act Density 0.006%

    No Known Activations