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

    Neuronpedia

    INDEX
    Explanations

    column and cell properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kork
    0.43
     کورٹ
    0.43
    yle
    0.41
     电
    0.38
     功能
    0.38
    Cxt
    0.37
    DockStyle
    0.37
    linkedExternal
    0.37
    ాప
    0.36
    opically
    0.36
    POSITIVE LOGITS
     fire
    0.46
     tirer
    0.45
     Fire
    0.45
    getColumn
    0.43
     fires
    0.43
    Fire
    0.41
     Tower
    0.40
     Smithsonian
    0.40
     rowIndex
    0.39
     tower
    0.39
    Act Density 0.004%

    No Known Activations