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

    Neuronpedia

    INDEX
    Explanations

    leadership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    包含
    -0.07
     теж
    -0.07
     attractive
    -0.07
    上了
    -0.07
     airing
    -0.06
     Leone
    -0.06
     control
    -0.06
    izando
    -0.06
     cookbook
    -0.06
     Control
    -0.06
    POSITIVE LOGITS
    .SelectedValue
    0.08
    ческого
    0.06
     procrast
    0.06
    νομ
    0.06
     фот
    0.05
    _DISCONNECT
    0.05
    цеп
    0.05
    طان
    0.05
    .IsChecked
    0.05
    profession
    0.05
    Act Density 0.048%

    No Known Activations