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

    Neuronpedia

    INDEX
    Explanations

    zone variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hik
    0.47
     fences
    0.43
     impresion
    0.42
     theseKeys
    0.41
     datasource
    0.41
     createElement
    0.40
     elementos
    0.39
     interrog
    0.39
     ditches
    0.37
     precisely
    0.37
    POSITIVE LOGITS
     Zone
    0.40
     зона
    0.40
    Zona
    0.38
    ม่
    0.37
     Zona
    0.37
    uncu
    0.37
     மண்ட
    0.37
    bücher
    0.36
     আহম
    0.36
     inadequ
    0.36
    Act Density 0.001%

    No Known Activations