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

    Neuronpedia

    INDEX
    Explanations

    apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Johnson
    -0.07
    -0.07
     ruler
    -0.07
    vox
    -0.06
     payroll
    -0.06
    _tw
    -0.06
    _free
    -0.06
     Ranger
    -0.06
     david
    -0.06
     Kimberly
    -0.06
    POSITIVE LOGITS
    ddie
    0.07
    .el
    0.06
    ськ
    0.06
    _AdjustorThunk
    0.06
    .vocab
    0.06
    Bs
    0.06
    .yang
    0.06
    ุงเทพ
    0.06
    urdy
    0.06
    μει
    0.06
    Act Density 0.011%

    No Known Activations