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

    Neuronpedia

    INDEX
    Explanations

    ask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noted
    -0.08
    iving
    -0.07
     prevalent
    -0.06
     Commerce
    -0.06
     Canadians
    -0.06
    }))↵
    -0.05
    ashed
    -0.05
    })↵
    -0.05
    !)↵
    -0.05
     recreation
    -0.05
    POSITIVE LOGITS
     мона
    0.09
    Checked
    0.07
    ListBox
    0.07
    *p
    0.07
    .legend
    0.06
    berapa
    0.06
     الهند
    0.06
    .control
    0.06
    _codigo
    0.06
     дод
    0.06
    Act Density 0.020%

    No Known Activations