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

    Neuronpedia

    INDEX
    Explanations

    administration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oltip
    -0.07
     touched
    -0.07
     pill
    -0.07
     gap
    -0.06
     zug
    -0.06
     harder
    -0.06
    ette
    -0.06
     методи
    -0.06
     hoje
    -0.06
    decrypt
    -0.06
    POSITIVE LOGITS
     administered
    0.09
     Conserv
    0.08
     baud
    0.07
     Administration
    0.07
    availability
    0.07
    *num
    0.07
    .Enabled
    0.07
     SM
    0.07
     availability
    0.07
    .CustomButton
    0.07
    Act Density 0.007%

    No Known Activations