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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lah
    -0.08
    193
    -0.07
    268
    -0.07
    194
    -0.06
    .BACK
    -0.06
     resto
    -0.06
    .Lo
    -0.06
    Ly
    -0.06
     ấy
    -0.06
     dese
    -0.06
    POSITIVE LOGITS
    atat
    0.07
     prevention
    0.06
    AndView
    0.06
    /display
    0.06
     prized
    0.06
     Suzanne
    0.06
    terminated
    0.06
     DisplayName
    0.06
     READ
    0.06
     Tina
    0.06
    Act Density 0.007%

    No Known Activations